The pivotal role of electrochemistry in biologically relevant systems is underscored by its ability to elucidate the chemical interactions occurring in neural networks of the brain. This has been significantly enhanced by advancements in electrochemical principles, spurred by the mid-20th-century technological revolution. Recent advancements in electrochemical methodologies have broadened their applications from mere measurement of neurochemical levels to encompassing modulation and simulation of brain signals, as well as monitoring neuronal electrochemical activities, thus paving the way for the application of implantable cerebral devices in the human brain. In this paper, a Deep Neural Network (DNN), as an Artificial Intelligence (AI) technique, was trained to recognize three distinct types of electrochemical signals derived from Electroencephalograph (EEG) measurements using an electrode array. Three classes of signals corresponding to the emotional states of sadness, happiness, and neutrality were successfully identified in a group of volunteers subjected to various psychological stimuli. The obtained results demonstrate an exceptional classification accuracy of 98.4% on the SEED database with a minimal array of sensors applied to the brain cortex, which serve as inputs for the artificial neural network.