Abstract Humans can perceive and learn new information from novel, previously unknown to them kinds of experiences, which can be very challenging for an artificial system. Here, a cognitive architecture is presented that uses its emotional intelligence to learn new concepts from previously unknown kinds of experiences. The underlying principle is that emotional appraisals of experience expressed internally as several MoNADs help the architecture to detect conceptual novelty and facilitate the generation and learning of new concepts. With the goal of measuring effects of emotional cognition on learning, the architecture was implemented in a robot and studied in a number of paradigms involving variable color settings. The key findings are the following. Initially, the dynamic state of the model neural network does not converge to some attractor when it receives an unknown kind of input. On the other hand, it quickly converges to an attractor in response to a familiar input. With time, the system develops the ability to learn previously unknown categories and concepts as new MoNAD. It is proposed that the model simulates a subliminal response of a human brain to an unknown situation. The findings have broad implications for future emotional artificial intelligence.