This study examines how people use emotion to communicate, emphasizing what happens after a mall shopping trip. Body language, subtle vocalizations, and facial expressions are all part of emotional communication; facial expressions are a common, natural, and dominant means of conveying emotional states. The difficulty, however, comes from the common patterns in human facial expressions, which make it hard to pick out subtleties with the unaided eye. The similarities between the looks of dread and astonishment demonstrate this. In response, this study aims to create an emotion identification model that can classify emotions based on facial expressions and recognize them instantaneously. CNNs, or convolutional neural networks, are used in the approach. CNN training incorporates dropout and batch normalization approaches to improve model generalization and reduce overfitting. They are considering the challenge’s multiclass classification structure. Ultimately, this research sheds insight into the complexities of human sentiments after a mall shopping experience and advances the construction of a robust emotion detection model.