This paper aims to explore and enhance ChatGPT’s abilities to generate more human-like conversations by taking into account the emotional state of the user. To achieve this goal, a prompt-driven Emotional Intelligence is used through the empathetic dialogue dataset in order to propose a more empathetic conversational language model. We propose two altered versions of ChatGPT as follows: (1) an emotion-infused version which takes the user’s emotion as input before generating responses using an emotion classifier based on ELECTRA ; and (2) the emotion adapting version that tries to accommodate for how the user feels without any external component. By analyzing responses of the two proposed altered versions and comparing them to the standard version of ChatGPT, we find that using the external emotion classifier leads to more frequent and pronounced use of positive emotions compared to the standard version. On the other hand, using simple prompt engineering to take the user emotion into consideration, does the opposite. Finally, comparisons with state-of-the-art models highlight the potential of prompt engineering to enhance the emotional abilities of chatbots based on large language models.