Sentience Quest: Towards Embodied, Emotionally Adaptive, Self-Evolving, Ethically Aligned Artificial General Intelligence

Current artificial intelligence systems -- from large language models to autonomous robots -- excel at narrow tasks but lack key qualities of sentient beings: intrinsic motivation, affective interiority, autobiographical sense of self, deep creativity, and abili ties to autonomously evolve and adapt over time. Here we introduce Sentience Quest, an open research initiative to develop more capable artificial general intelligence lifeforms (AGIL) that achieve these grand challenges with an embodied, emotionally adaptive, self - determining, living AI, with core drives that ethically align with human s and the future of life. Our vision builds on ideas from cognitive science and neuroscience -- from Baars' Global Workspace Theory and Damasio's somatic mind, to Tononi's Integrated Information Theory and Hofstadter's narrative self -- synthesizing these into a novel cognitive architecture. We describe an approach that integrates intrinsic drives (e.g., survival, social bonding, curiosity), a global "Story Weaver" workspace for internal narrative and adaptive goal pursuit, and a hybrid neuro - symbolic memory that logs the AI's life events as structured "story objects." Implemented in humanoid robots like Sophia, this architecture enables adaptive behavior grounded in a human - like body, in pursuit of experiential learning homologous to human experiences. Early resu lts are promising, with a driver - based goal system generating self - motivated actions, a narrative memory allowing the robot to refer to its own experiences, and integrated information measures (Φ) quantifying evolving cognitive integration. We discuss ethi cal implications, exploring how co - evolution with humans via an information - centric ethics ("SuperGood" principle) may guide both developers and AI systems to ensure value alignment. Sentience Quest is presented as a call to action: a collaborative, open - source effort to imbue machines with accelerating sentience in a safe, transparent, and beneficial manner. 2