She sat frozen on the park bench, the notification on her phone a burning brand in her hand. The gentle breeze, normally a welcome caress, now felt like icy needles against her skin. People strolled by, oblivious, laughing, living their lives. How could they not know? Didn't they feel the earth tilting on its axis?

Tears, hot and relentless, streamed down her face. She couldnโ€™t stop them. She scrubbed at her cheeks with the back of her hand, smearing mascara and making the situation worse. Each sob wracked her body, a violent earthquake of grief and disbelief.

She clutched her phone tighter, the screen a distorted reflection of her ravaged face. She needed to see her, to hear her voice. She scrolled through their photos, each image a fresh stab of pain. She had to talk to her. Immediately. She had to *fix* this.

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