ABSTRACTA non-default interpretation is required whenever speakers creatively depart from established norms and defaults. But effective speakers do not travel alone when they move away from default meanings to novel, non-default destinations. Effective speakers bring their readers with them, sometimes by making the non-default destination the only meaningful destination that can be reached with an utterance, but other times by helpfully—if subtly—marking their utterances to facilitate the dislocation of words and meanings. We consider the relative utility of different indicators of non-defaultness in this article, ranging from the subtle to the overt. Our approach argues for the usefulness of machine-generated texts when quantitatively exploring aspects of human linguistic creativity, since machine-tooled utterances can better assure the consistency and comparability of novel utterances that are designed to offer strikingly original points of view. Within this mechanical framework, we measure the extent of the shift from default to non-default interpretations via the downshift from positive to negative affect in machine-generated ironic utterances. In using machine-generated texts, our approach and its results also argue for the possibility that intelligent machines can craft creative utterances of their own, and effectively communicate an ironic point-of-view to human readers.