The design of efficient electroencephalogram (EEG) classification systems for the detectionof mental states is still an open problem. Such systems can be used to provide assistance to humansin tasks where a certain level of alertness is required, like in surgery or in the operation of heavymachines, among others. In this work, we extend a previous study where a classification system isproposed using a Common Spatial Pattern (CSP) and Linear Discriminant Analysis (LDA) for theclassification of two mental states, namely a relaxed and a normal state. Here, we propose an enhancedfeature extraction algorithm (Augmented Feature Extraction with Genetic Programming, or+FEGP)that improves upon previous results by employing a Genetic-Programming-based methodologyon top of the CSP. The proposed algorithm searches for non-linear transformations that build newfeatures and simplify the classification task. Although the proposed algorithm can be coupled withany classifier, LDA achieves 78.8% accuracy, the best predictive accuracy among tested classifiers,significantly improving upon previously published results on the same real-world dataset.