Psychological well-being (PWB) is a multidimensional construct encompassing emotional, cognitive, personality, and social factors, playing a crucial role in mental health and quality of life. While previous research has examined the relationships between PWB and psychological traits, the natural clustering of well-being profiles remains underexplored. This study applied Affinity Propagation (AP) clustering, an unsupervised machine learning (ML) technique, to identify distinct well-being profiles in 685 young adults from the Human Connectome Project (HCP). A composite PWB score from the NIH Toolbox Emotion Battery was used to assess its associations with cognitive functions, personality traits, emotional health, and psychiatric and behavioral factors. Four PWB clusters emerged: Low, Medium-low, Medium-high, and High. Lower PWB was linked to higher negative affect (anger, sadness) and greater neuroticism, while higher social support, extraversion, agreeableness, and conscientiousness characterized greater well-being. Cognitive abilities did not significantly differentiate clusters, suggesting well-being is primarily influenced by emotional, social, and personality factors. By integrating ML with statistical analyses, this study provides a data-driven understanding of well-being, emphasizing the need for targeted interventions to enhance emotional resilience, social connections, and mental health support.