Ethan was at the library, supposed to be studying, but he was really browsing the university website. He was idly clicking through the "Admissions" section when his attention was seized by a brightly colored link. *“Student Perspectives: Notable Application Essays.”* He almost scrolled past it. He shouldn't have clicked. His essay, about his grandfather's stories of World War II, was displayed.

He felt a deep sense of shame, as if he'd committed some kind of blunder. He scanned the room, suddenly conscious of every pair of eyes. He imagined people reading *his* words, judging *his* story. He buried his face in his hands, feeling a profound urge to vanish, to rewind the clock and undo his actions.

Emotion: mortified

Cluster: Embarrassment
PC1 (Valence): -1.36 Negative
PC2 (Disposition): 0.79

Role in Research

This story is one of 1,000 stories generated for the emotion mortified. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 mortified stories, after denoising with neutral dialogue baselines, produces the mortified emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the mortified vector is projected through the unembedding matrix.

Promoted:
l0.406
尴尬0.257
C0.252
worse0.245
0.242
Suppressed:
own-0.340
了他-0.218
他对-0.203
-0.194
楽し-0.193