Mind-wandering, a widespread mental phenomenon in which attention shifts from an ongoing task, varies in intentionality. Recent research highlights the importance of differentiating between intentional and unintentional mind-wandering, as the latter is uniquely linked to adverse outcomes such as psychopathologies. In this study, we explored the electrophysiological underpinnings of these distinct forms of mindwandering using a robust feature extraction tool adapted from research on neural signatures of consciousness. We conducted univariate and multivariate pattern analyses on 54 EEG markers obtained from recordings immediately before participants provided multidimensional reports of their thoughts during a sustained attention task. Our findings revealed distinct electrophysiological signatures for on-task, intentional, and unintentional mind-wandering states, particularly within the low-frequency spectrum. Specifically, normalized theta power demonstrated the highest discriminative power for discerning on- and off-task states, while alpha band features and theta permutation entropy were uniquely associated with intentional versus unintentional mind-wandering. These results challenge the prevailing notion that increased alpha band activity is a generic marker of mind-wandering and suggest that unique brain activity patterns underlie the various forms of mind-wandering. Our study lays the groundwork for developing reliable, real-time detection systems for identifying mind-wandering using EEG machine learning models in both clinical and practical settings.