The news had hit Emily like a physical blow. She sat at her desk, staring at the screen, unable to process what she was reading. Her mouth was dry, her throat tight. She couldn't swallow. A strange buzzing filled her ears.

She felt a sudden urge to clean. She stood up and frantically began to tidy her already-pristine desk, rearranging pens and organizing files. She wasnโ€™t sure why, but the action gave her something to focus on.

But the thoughts kept swirling, the accusations echoing in her mind. She started to hum a tune to try and calm herself. The tune failed to work. She felt her chest constrict.

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