Abstract: Affective computing is an important research direction in the future field of artificial intelligence. Although large language models（LLMs）have solved many problems in natural language processing, there remains a significant gap in understanding human emotions. False-concealment emotions are one of the aspects of fine-grained sentiment analysis. In the context of big data on social network public opinion, users with false-concealment emotions often conceal their true intentions, and these users play a role in amplifying the development of public opinion. Discovering false-concealment emotions and understanding their intentions hold significant scientific importance and practical value for accurately grasping the evolution of public opinion and controlling its direction. The main contributions of this paper are as follows: starting from an analysis of the phenomenon of pseudo-concealment emotions in the context of social networks, we define false-concealment emotions; based on Ekman's six basic emotions theory, we establish a formal model of false-concealment emotions; we explore the key challenges in identifying false-concealment emotions and discovering their intentions; we review prior research on false-concealment emotions; and we outline the main future research directions for false-concealment emotions in the field of artificial intelligence.