The overhead lights flickered, casting long, dancing shadows that seemed to mock her. The air was thick with the scent of stale coffee and… him. She could smell his cologne, a scent she'd always secretly liked, now a source of intense distress. She kept her gaze fixed on the digital display, as if willing the numbers to change faster.

She considered every interaction she’d ever had with him, analyzing each word, each gesture, each perceived slight. Her cheeks felt hot, and she could feel a nervous sweat beading on her forehead. The memory of the email she'd accidentally sent to him last month, professing her love for her cat, was now circulating on a loop inside her brain.

“This is quite the predicament, huh?” Ben asked, breaking the silence.

She offered a tiny, strained laugh, hoping he wouldn’t probe further.

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