The school pick-up line felt narrower today, the cars closing in. Sarah gripped the steering wheel so hard her knuckles were white. Mr. Henderson? Her son, Leo, would be in *Mr. Henderson’s* class. Panic clawed at her throat.

She hadn't seen the man in twenty years, not since… well, since her own disastrous fifth grade year. A shudder ran through her, a cold ripple that began at her spine. She imagined Leo, small and vulnerable, facing that same stern gaze, the same sharp-tongued criticisms she'd endured.

"Leo!" she called, her voice sounding thin and reedy. He ran towards the car, a bright smile on his face. She forced a smile in return, but the muscles in her face felt stiff, unnatural.

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