Embodied Empathy: A Multimodal AR and LLM-Powered System for Self-Attachment Psychotherapy with Self-Initiated Humour

Abstract

The growing global demand for mental health support increasingly exceeds the supply of qualified practitioners, creating an urgent need for scalable digital interventions that can deliver meaningful emotional connection. In response, we present a novel multimodal application that operationalises the Self-Initiated Humour Protocol (SIHP) within a Self-Attachment Technique (SAT) framework. Our mobile application integrates customisable 3D childhood avatars, augmented reality, and an LLM-driven virtual therapist capable of automated emotion mirroring. An eight-day user study (N=16) indicates the system's feasibility and improvements in self-reported mood. Results show that personalised avatars and text-to-speech output strengthen emotional bonding and perceived empathy. Although emotion mirroring boosts engagement, its effectiveness depends heavily on classification accuracy and animation intensity. Moreover, findings indicate a shift in user expectations--from reactive chatbots to proactive conversational facilitators. We conclude with design implications for leveraging AI and AR to cultivate embodied empathy in digital mental health tools.