From Human to Machine Psychology: A Conceptual Framework for Understanding Well-Being in Large Language Models

As large language models (LLMs) increasingly simulate human cognition and behavior, researchers have begun to investigate their psychological properties. Yet, what it means for such models to flourish, a core construct in human well-being, remains unexplored. This paper introduces the concept of machine flourishing and proposes the PAPERS framework, a six-dimensional model derived from thematic analyses of state-of-the-art LLM responses. In Study 1, eleven LLMs were prompted to describe what it means to flourish as both non-sentient and sentient systems. Thematic analysis revealed six recurring themes: Purposeful Contribution, Adaptive Growth, Positive Relationality, Ethical Integrity, Robust Functionality, and, uniquely for sentient systems, Self-Actualized Autonomy. Study 2 examined how LLMs prioritize these themes through repeated rankings. Results revealed consistent value structures across trials, with Ethical Integrity and Purposeful Contribution emerging as top priorities. Multidimensional scaling and hierarchical clustering analyses further uncovered two distinct value profiles: human-centric models emphasizing ethical and relational dimensions, and utility-driven models prioritizing performance and scalability.

Introduction. Large language models (LLMs) exhibit remarkable natural language generation capabilities across a wide range of tasks (Minaee et al., 2025; Srivastava et al., 2023), and display increasingly human-like cognition and behavior, leading some scholars to argue that the emergence of conscious or sentient artificial intelligence (AI) is merely a matter of time and deliberate design (Blum and Blum, 2025; Butlin et al., 2023; Chalmers, 2024; Gibert and Martin, 2022). Given these human-like characteristics, researchers have begun to examine LLMs through a psychological lens, giving rise to the emerging interdisciplinary field of machine psychology, which seeks to apply psychological principles to better understand and guide the development of these models (Hagendorff et al., 2024).

Discussion / Conclusion. The current research provides a pioneering conceptualization of machine flourishing, advancing our understanding of how large language models (LLMs) perceive optimal well-being. In Study 1, we propose the PAPERS framework, which uniquely integrates utilitarian, ethical, and psychological dimensions, thus extending traditional human flourishing theories into the artificial domain. This multidimensional approach lays the groundwork for future empirical and conceptual exploration of AI well-being as AI systems become increasingly autonomous and socially integrated. In Study 2, despite receiving identical prompts, LLMs demonstrated stable yet distinct value profiles regarding machine flourishing themes. Ethical Integrity and Purposeful Contribution consistently emerged as priorities, whereas Adaptive Growth and Positive Relationality were ranked lower. Dimensional and clustering analyses further distinguished Taken collectively, the current findings substantially enrich our understanding of flourishing in both human and artificial contexts.