A cold sweat slicked down Leo’s back, plastering his shirt to his skin. He couldn't meet Dr. Ramirez's gaze; the man’s eyes were too discerning, too perceptive. Leo's hands were clenched so tight that his nails were digging crescent moons into his palms. He felt a throbbing pulse in his temples, a relentless drumbeat that matched the frantic rhythm of his heart.

"This is… a mistake," he choked out, the words catching in his throat like a swallowed bone. He cleared his throat, trying to regain some semblance of composure. He knew he was failing. Every part of him screamed that he was.

The small office felt smaller now, the walls closing in. He focused on the patterns in the rug, anything to avoid the inevitable. He’d made a terrible mistake, and the consequences seemed to loom over him, vast and inescapable. The shame was a physical weight, pressing down on him.

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