The tiny space felt like a pressure cooker. The air grew thick, hot, and stale. Michael felt a tremor start in his legs, spreading up to his chest. He clenched his jaw, trying to stop the tremors from reaching his hands, he failed. He hated this. He hated enclosed spaces.

"Don't worry," said his colleague, Susan, her voice tight. "They'll get us out." But her face was as pale as his, and she couldn't meet his eyes.

He imagined the worst. He imagined them staying here. Forever. He started to tremble, his teeth chattering uncontrollably. His eyes darted around the elevator, cataloging every detail, every potential escape route. There were none.

He began to mutter under his breath, a stream of fragmented phrases he wasn't even conscious of speaking. He wanted out. Now.

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