Emotion analysis often involves the categorization of isolated textual units, but these are parts of longer discourses, like dialogues or stories. This leads to two different established emotion classification setups: (1) Classification of a longer text into one or multiple emotion categories. (2) Classification of the parts of a longer text (sentences or utterances), either (2a) with or (2b) without consideration of the context. None of these settings, does, however, enable to answer the question which emotion is presumably experienced at a specific moment in time. For instance, a customer’s request of “My computer broke.” would be annotated with anger. This emotion persists in a potential follow-up reply “It is out of warranty.” which would also correspond to the global emotion label. An alternative reply “We will send you a new one.” might, in contrast, lead to relief. Modeling these label relations requires classification of textual parts under consideration of the past, but without access to the future. Consequently, we propose a novel annotation setup for emotion categorization corpora, in which the annotations reflect the emotion up to the annotated sentence. We ensure this by uncovering the textual parts step-by-step to the annotator, asking for a label in each step. This perspective is important to understand the final, global emotion, while having access to the individual sentence’s emotion contributions to this final emotion. In modeling experiments, we use these data to check if the context is indeed required to automatically predict such cumulative emotion progressions.