The drive felt endless, each mile stretching into an excruciating eternity. Her knuckles were white as she gripped the steering wheel, her shoulders tense, her jaw clenched. A wave of nausea rolled through her. She was late, and she knew he'd be waiting.

She pulled into the driveway, the tires crunching on the gravel. Before her sat the house. The same house, the same overgrown lawn and the same menacing oak tree, that had been the backdrop to her childhood torment. The nameplate on the door read, “Dr. Kevin Miller, LPC."

Kevin Miller. His name conjured vivid images of her worst years, the sting of insults, the crushing weight of humiliation. She could barely breathe.

Emotion: distressed

Cluster: Fear / Anxiety
PC1 (Valence): -2.39 Negative
PC2 (Disposition): -0.52

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.304
😞0.296
worse0.291
😖0.285
😰0.276
Suppressed:
de-0.457
la-0.349
:)-0.239
B-0.232
happy-0.229