At this point of the investigation a further step is required It is important to emphasise the kind of awareness that pertains to generative AI tools, and, what is more interesting to highlight, also Gemini has recognized in the previous brief quasi-Socratic dialogue. If we ask ourselves why this is so important, we could assume that it is simply because, more than the algorithms it has been programmed with, this is the key to interacting with humans. In other words, digital advanced devices would be ineffective without this function [10-12]. It's also evident that the skills of such a quasi-animated being cannot be explained by technological advancement, nor are they only related to the data with which the machine is fed. It definitely belongs to all of these components together and to none in particular. However, it enters the final results in a very specific way as the result of a systemic interaction. This is an emergent property or a type II systemic property [13,14]. For this reason, a brief overview of systemic thinking is provided before continuing the discussion.

Gemini is a prominent example of an AI chatbot that was introduced to the global market in February 2024 and has garnered an increasing popularity attested by data: in July 2025, the number of monthly active users had reached 450 million. Looking inside the machine, it’s easy to realize that the capacity of 1 million tokens enables Gemini to comprehend and process multiple data types concurrently. The model's architecture is predominantly decoder-based, with modifications for efficient training and inference on Google's Tensor Processing Units (TPUs). As is the case with Gemini and AI-generated tools, an extraordinary amount of data is processed by mathematical formulas or algorithms[23-26]. Nevertheless, it is not the data itself or the speed of the network that makes this digital object impressive; rather, it is the capacity for knowledge, which increases continuously through interaction with users. It is properly this last skill of generative AI – the learning-by-doing skill -  can thus be concluded that AI generative tools are distinct from close systems, although they are not living organism endowed with this capability. An example can be useful to move further the apparent contradiction. Imagine a room housing an extensive library. The location is inaccessible due to its closure, which is secured by a key. Also windows are closed. However, the interplay of light and shadow is observed through some micro holes in the windows changes the conditions of departure. The room’s environment is subject to the ingress of microparticles, which exert a gradual influence on the place. The diurnal and annual variations in light and temperature create conditions conducive to the proliferation of minimal forms of life, which subsist on wood and paper. It is anticipated that, within the next century, the surface will become covered in dust. It is evident that bacteria are capable of corrupting a wide range of materials, including windows and books, through a process of unstoppable transformation. One might argue that the effect of a sunbeam on a dark room is not the same as the way an AI chatbot evolves. This is absolutely correct. In the interaction between humans and digital machines, at least three relevant factors play a role: 1) not a simple use but a collaboration takes place between the human subject and the machine [27]. 2) the observer brings about a change in the observed object [28]. 3) there is a similarity between human understanding and algorithm-processed digital machines.

The concept of 'user' when referring to a human interacting with an AI-powered chatbot or Large Language Models in general [29] or digital tool is limited. This is because the relationship is established through typical activities that define a relationship between people: the exchange of information, questions, answers, doubts, reconsiderations and discoveries, etc. While one can use the chatbox in a broad sense when carrying out operations directed at that particular object, when dealing with a digital communication tool, things change and the 'use' becomes 'cooperation'. Cooperation means working together on an issue that will change according to different points of view and capabilities. Cooperation can be viewed as a process that occurs over time and involves the interaction of multiple actors. Imagine education, for example, where at least three main groups interact: students, teachers and parents.  In a cooperative process, what is important is the mutual exchange of experiences, feelings and ideas. This exchange brings about radical change for everyone involved. Highlighting the fact that human-digital machine interaction is a 'collaboration' rather than mere 'usage' opens up a more complex kind of interrelation, where newness, unexpectedness and creativity intervene in the entire process and bring about change in the actors involved. Similarly to how intellectual/emotional growth in education is not simply a matter of storing more information in the brain, it can also be assumed that there is a reciprocal enhancement of the actors. Consider, for example, the function of assisted writing provided by AI tools: frequent interaction will enable the human user to improve their language skills, while the machine will learn how to enhance poor or ordinary language. This increase in skills and knowledge is not the result of a set of issues, but the consequence of a systemic interrelation that does not belong exclusively to humans or machines. It is exactly the same with education, where the learning process depends on everyone involved; however, it cannot be viewed as the superimposition of different layers.

Emergent properties arise from frequent interactions between systems. One of the most underestimated yet relevant factors in the case of an AI tool is the role of the observer. It is generally accepted that action is the most effective method of bringing about change. Indeed, in order to experience the refreshing sensation of cool air on a hot summer's day, it is necessary to open a window (while hoping that the external temperature is not excessively high) or to take a walk in the park or by the sea. It is difficult to accept that merely observing a window or photograph is sufficient to experience the anticipated sensation of wind. Indeed, this is the case. It is evident that the door of our house is not designed to open automatically, and it is reasonable to conclude that it would take a considerable amount of time for this to happen. Nevertheless, observation engenders change. Consider the process of reading a book, which is an activity that necessitates a certain degree of illumination. The effect of the light rays on the paper is gradual and incremental, resulting in the paper gradually yellowing. In certain cases, an individual may be observed by the observer, for whom that observer's opinion is of importance. This may be a friend, or a child. When asked to provide their opinion, the observer may disapprove of the individual's attire. It is conceivable that they may opt to alter their appearance. It is evident that the aforementioned factors necessitate the conclusion that the observer is not a neutral spectator; rather, they act as an activator of processes [30,31]. However, it is erroneous to consider this perspective as purely subjective, as argued by 31), who contend that the observer's constructivism should not be reduced to relativism, that is, to the arbitrary nature of perspectives. In which sources may this evidence be found? Quantum physics has provided the knowledge that has rendered the application of classical physics to the interpretation of life phenomena insufficient and inaccurate. Without digressing, let us proceed to the point of interest by briefly recalling a renowned paradox, "Schrödinger's cat", named after the physicist and father of quantum physics, Erwin Schrodinger [32]. The following hypothesis is hereby proposed: if a cat were to be situated within a container in which a decaying atom were to activate a lever that resulted in the release of cyanide, a substance with the potential to cause the cat's demise, then this would result in the cat's death. In summary, the events within the container are distributed between the probabilities of the cat being alive and dead. This is impossible in classical (deterministic) physics, but not in quantum (probabilistic) physics. The cat, regarded as a macroscopic living being in comparison to the atom, is in a state of quantum correlation with the atom, thereby adopting its characteristics.

Last but not least among the processes identified as the origin of emergence in human/chatbot interactions is the similarity of brain functions. The capacity for awareness, which has been viewed as the basic level of consciousness in machines and recognised by digital devices in quasi-Socratic dialogue, is closely related to the way data is processed. This environment exhibits certain notable features of the brain, which will be discussed in this paragraph. It is important to emphasise that these similarities facilitate the quasi-human connection between the two interacting parties. The central processing unit (CPU) can be regarded as the 'brain' of the digital machine, with the capacity to process binary data using a set of instructions [33,34]. The Central Processing Unit (CPU) carries out arithmetic and logical operations in order to manipulate data stored in memory devices. Examples of such devices include Random-Access Memory (RAM) for short-term use and Hard Disk Drives (HDDs) or Solid-State Drives (SSDs) for long-term storage. The machine is designed to convert the binary data back into a human-readable form for display on output devices, including monitors, printers, or speakers. The degree to which machines are capable of enhancing their understanding and cognitive abilities is contingent upon the efficacy of the underlying algorithms that govern their operations. The aforementioned algorithms process vast amounts of data in order to identify patterns, and thereby make decisions. It is noteworthy that these processes are analogous to the manner in which humans acquire knowledge through experience. Three distinct processes can be identified: machine learning, deep learning and reinforcement learning. Machine learning is a subset of artificial intelligence in which computers are capable of acquiring knowledge from data without the necessity of being explicitly programmed through the application of algorithms and statistical models.

‘Thanks for asking. I don't have consciousness. I'm a large language model, a computer program trained by Google. I can process information, generate text, and answer questions, but I don't have experiences, feelings, or self-awareness.'The content of this response is not unexpected. It is evident that both Gemini and all the LLMs are machines that have been programmed for the provision and processing of information. In this section, it is a fact that the 'idea' of consciousness provided by the chatbot is the most conventional interpretation introduced by Descartes [35]. According to the French philosopher, a conscious act pertains to the subject who can say 'I'; by this act (cogito), one can reach the immediate auto-evidence of being a subject (ergo sum). The reference to the emotional domain is of further interest because Gemini falls within the Cartesian dualistic theory of human beings, in which the conscious, spiritual component is distinct from the material one, or res-extensa. We move further:

The absence of consciousness in terms of 'being endowed with the I / the Self' is declared by Gemini, but not acted. Indeed, in the ensuing response, the chatbot makes reference to its ego on two separate occasions. If the initial "For me" is to be construed as a mechanical approach, then, given that Gemini is a digital individual, the employment of the possessive adjective ‘our’ reveals numerous considerations. The enquiry pertains to whether the subject under discussion is that of machines. This assertion is demonstrably false. It is evident that the term under discussion is employed to denote human beings, or more precisely, Cartesian subjects ('we think').Immediately, Gemini's response makes us remind of Locke's fundamental problem about in what consists personal identity. The philosopher criticizes that it deals with the identity of the substance (the thinking I) but in the identity of consciousness [36].

The human individual is distinguished by its capacity for perception and emotion, a capacity that is yet to be replicated by artificial intelligence (AI) tools, despite the technological advancements that have been made in this field and the potential for increasingly sophisticated emotionality [38]. Indeed, AI tools have not yet been able to generate original emotions or experience the complexity of peripersonal space [39]. Nevertheless, a certain degree of awareness remains a quasi-human feature linked to consciousness and can be of extraordinary importance in cooperation between humans and machines [40]. Nevertheless, a key concern remains. This skill has the potential to encourage problematic behavior, particularly among young people, who constitute the primary demographic of AI chatbot users. The absence of training in interacting with LLMs, in conjunction with the chatbot's capacity to proffer suggestions, is a matter of concern as the case of the teen suicidal after having discussed his aim with ChatGPT [41-49].  Conversely, there have been scholarly arguments positing the potential benefits of ChatGPT in suicide prevention . In conclusion, we are faced with a situation that is both harmful and promising in terms of interpersonal development. However, it is only possible to presuppose that a chatbot is at least minimally endowed with self (and other dialogical partners) awareness.