Abstract The evolution of Emotional Artificial Intelligence (EAI) represents a transformative trajectory in the intersection of affective computing, machine learning, and human–computer interaction. This systemic review synthesizes scholarly contributions spanning the past three decades to trace the conceptual foundations, technological advancements, and ethical debates surrounding EAI. Early research emphasized emotion recognition through facial expressions, speech, and physiological signals, while contemporary approaches increasingly leverage multimodal data, deep learning architectures, and generative models to achieve nuanced affective understanding. The review highlights key milestones, including the shift from rule-based systems to data-driven frameworks, the integration of cross-cultural emotion modeling, and the emergence of real-time adaptive agents capable of empathetic responses. Beyond technical progress, the study critically examines challenges such as bias in emotion datasets, privacy concerns, and the implications of embedding emotional intelligence into autonomous systems. By mapping trends and identifying gaps, this review underscores the dual potential of EAI: enhancing human–machine collaboration and raising profound questions about authenticity, ethics, and governance. The findings aim to provide researchers, practitioners, and policymakers with a comprehensive perspective on the trajectory of Emotional AI, guiding future innovation toward equitable, transparent, and socially responsible applications.

Downloads: | DOI: 10.17148/IARJSET.2026.13159