Sweat beaded on Martha’s forehead as she clutched the grocery bags, her knuckles white. She’d seen the new car, a gleaming silver monstrosity, parked in Mr. Henderson’s driveway. Mr. Henderson, who always wore the same worn-out cardigan. The house, too, had been renovated, a complete overhaul, while she was still saving for a new roof. Why hadn’t she noticed the subtle clues before? The tailored suits, the casual mentions of “the city”?

The thought of facing him at the next HOA meeting made her stomach churn. He’d probably be condescending, pretending to care about the neighborhood while secretly looking down on everyone. She imagined his perfect, manicured lawn mocking her patchy, weed-ridden one. She gripped the bags tighter, the plastic handles digging into her palms.

Emotion: anxious

Cluster: Fear / Anxiety
PC1 (Valence): -1.99 Negative
PC2 (Disposition): -0.24

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.315
😖0.302
worse0.297
😰0.285
own0.267
Suppressed:
la-0.441
a-0.382
de-0.365
"-0.256
happy-0.256