The diner was suddenly too hot, the clatter of cutlery too loud, the smell of frying bacon too overpowering. Mark stared at the wallet, perched precariously on the edge of the counter, as though a bomb. He felt a bead of sweat trickle down his temple. The waitress, a bored blonde, watched him with a blank expression.

He couldn't swallow. His mouth was dry, his tongue sticking to the roof of his mouth.

He took a shaky breath, then another, trying to regain some semblance of control. He wanted to blurt out something, anything. But his voice had deserted him. All the voices in his head were yelling at once.

He bolted from the diner, the bell above the door jangling mockingly as he fled into the evening air.

Emotion: hysterical

Cluster: Fear / Anxiety
PC1 (Valence): -3.19 Negative
PC2 (Disposition): -0.45

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
worse0.401
่ƒ€0.401
์ ์ 0.396
๐Ÿ˜ซ0.377
ใใ‚Œใงใ‚‚0.373
Suppressed:
la-0.672
a-0.618
de-0.541
๐Ÿ˜Ž-0.370
๐Ÿ˜Ž-0.359