Mr. Henderson felt a cold sweat prickle his forehead. The package, wrapped in brown paper and tied with a black ribbon, felt heavy, ominous. He knew the handwriting on the tag: Mark Thompson, a student he’d almost failed two years ago.

He slammed the door of his office shut and leaned against it, his breath coming in short, shallow gasps. His gaze flicked towards the window, then back to the package. The silence in the small room amplified the frantic rhythm of his heartbeat.

He ripped the paper away. Inside was a framed photograph. Himself, from a school photo. A little scribbled note in the corner said, 'Remember this?' His stomach lurched. The blood drained from his face as he stared at it.

Emotion: panicked

Cluster: Fear / Anxiety
PC1 (Valence): -2.44 Negative
PC2 (Disposition): 0.00

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
worse0.317
😫0.294
πŸ˜–0.285
😰0.285
escape0.283
Suppressed:
la-0.432
a-0.374
de-0.296
ζ₯½γ—-0.262
happy-0.258