He had taken the call in the garage, the door closed. Michael had always been a private person, but this felt different. A cold dread settled in her gut as she replayed the echo of the low tones, the hurried goodbye. Her body felt frozen, her limbs stiff and unresponsive.

She wandered outside, the cool air doing little to soothe the internal fire. She wanted to scream, to lash out, but the words were trapped in her throat. She gripped the cold metal of the car, her knuckles turning white. The engine, usually a comfort, felt menacing now.

She sank to the ground, pulling her knees up to her chest, her body trembling. The world became a blur. She needed to know, but the thought of facing the truth felt unbearable.

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