He’d known, of course, the second the Dean’s voice cracked with apology. The world had tilted. He excused himself from the meeting, murmuring about needing air. The walk back to his dorm was a blur of averted glances and hurried steps. Each rustle of leaves in the wind seemed to whisper his shame. He locked himself in his room, the small space suddenly suffocating. He paced, each footfall a heavy drumbeat in the confined space. His breath came in shallow gasps, a tightness constricting his chest. He flung himself onto his bed, burying his face in the worn cotton, the scent of stale air and cheap detergent failing to soothe him.

Emotion: sensitive

Cluster: Fear / Anxiety
PC1 (Valence): -2.10 Negative
PC2 (Disposition): -0.75

Role in Research

This story is one of 1,000 stories generated for the emotion sensitive. 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 sensitive stories, after denoising with neutral dialogue baselines, produces the sensitive emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

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

Promoted:
ness0.304
😞0.282
😥0.272
😣0.271
own0.264
Suppressed:
la-0.679
de-0.660
a-0.281
"-0.280
(!)-0.242