"Did you see the news?" Her friend, Karen, looked at her with wide eyes. "They arrested the CEO of that investment firm! Turns out he was laundering money!" The newscaster was showing an image of the firm. There in the background, standing next to the CEO in the picture, was her friend, Susan. Susan, who had always said she was a part-time yoga instructor.

Her hands started to shake. The room seemed to tilt. She felt a wave of nausea wash over her. It was a cold, horrible shock. She’d told Susan about her struggles, her worries, and Susan had listened, nodding sympathetically.

She scrambled for her phone, her fingers clumsy and unresponsive. She felt as if she had been hit by a truck. The image on the screen was burned into her mind, a horrifying revelation.

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