Sweat beaded on Martha’s forehead, despite the arctic air conditioning. They'd summoned her to the manager's office this morning and, after a brief, cheerful preamble about "new opportunities," had introduced her replacement, a fresh-faced college grad named Kevin. Now, she was supposed to show Kevin the ropes. The fluorescent lights seemed to buzz louder, a high-pitched whine that threatened to shatter her teeth. She found herself clutching her stomach, nails digging in. "Okay, so, uh… the coffee machine," she began, her voice cracking like dry leaves.

Kevin, bless his heart, nodded with eager enthusiasm. She jabbed a trembling finger at the buttons, the plastic cool and unfamiliar under her touch. Her gaze darted around the room, as if expecting something terrible to leap out. The spreadsheets, the files, the endless emails… all a sudden, crushing weight on her shoulders. She just wanted to run, to vanish.

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
0.401
점점0.396
😫0.377
それでも0.373
Suppressed:
la-0.672
a-0.618
de-0.541
😎-0.370
😎-0.359