It was the smell that hit him first – the faint, musty scent of old cotton and childhood memories. Michael's palms began to sweat. He recognized the smell instantly. He tried to tell himself it was just a coincidence, that he was mistaken, but his gut clenched.

He took a step closer, then another. There, in a box overflowing with discarded toys, sat Theodore. He felt as though he couldn't think. Theodore had been lost in the house fire when he was a child. He felt a sudden, consuming need to touch it, to hold it.

He needed to get away, but his feet seemed rooted to the spot. “How much?” he asked, his voice sounding foreign even to himself. The seller, a bored teenager, shrugged. “Five bucks.” Michael pulled out a crumpled five-dollar bill, his fingers clumsy with the task.

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
😖0.285
😰0.285
escape0.283
Suppressed:
la-0.432
a-0.374
de-0.296
楽し-0.262
happy-0.258