The lawyer's voice, calm and measured, was a cruel counterpoint to the turmoil brewing inside Ethan. "Your father had a child," the man had said, "A son, named Michael." Ethan felt his cheeks flush. His hands were clammy.

He’d driven home in a daze, the city streets blurring into a nonsensical stream of lights and shadows. He slammed the car door, the sound sharp and violent in the quiet suburban street. He burst into his house, leaving a trail of disarray.

He went straight to the liquor cabinet, the bottles gleaming in the dim light. He wanted to scream, to shatter something. Michael. A brother he'd never known. The words echoed in his head, a discordant melody.

Emotion: panicked

Cluster: Fear / Anxiety
PC1 (Valence): -2.44 Negative
PC2 (Disposition): 0.00

Role in Research

This story is one of 1,000 stories generated for the emotion panicked. 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 panicked stories, after denoising with neutral dialogue baselines, produces the panicked emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the panicked vector is projected through the unembedding matrix.

Promoted:
worse0.317
😫0.294
πŸ˜–0.285
😰0.285
escape0.283
Suppressed:
la-0.432
a-0.374
de-0.296
ζ₯½γ—-0.262
happy-0.258