This work presents the participation of the Intelligent Systems Group (GSI) at Universidad Politécnica de Madrid (UPM) in the Emotion Analysis competition EmoEvalEs, part of IberLEF 2021 Conference. The addressed challenge proposes an emotion classification task of Spanish tweets, categorizing each message into seven emotions. We pro- pose the design and development of a fine-tuned neural language model (XLM-RoBERTa) to tackle this challenge. We have obtained excellent results with this approach, obtaining the first place in the competition with a macro-averaged F1 score of 71.70%. Additionally, we also explore the application of several ensemble methods built over the neural language model.