The coffee tasted like ash in Clara's mouth. She couldn't remember the last time she'd been able to eat a proper meal. Sleep had become a distant memory, replaced by a restless tossing and turning. The promotion was everything, but the competition felt crushing.

She found herself constantly checking her phone, hoping for an update, any clue. She tapped her pen against the desk incessantly, the rhythmic sound grating on her nerves. She kept catching her co-worker, Mark, observing her, a smirk playing on his lips. His ambition was palpable.

She'd caught a glimpse of her reflection in the elevator mirror that morning – her eyes were sunken, dark circles shadowing beneath them. She had the distinct feeling of being on the verge of imploding.

Emotion: worried

Cluster: Fear / Anxiety
PC1 (Valence): -2.02 Negative
PC2 (Disposition): -0.43

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
worse0.285
S0.279
😰0.277
😣0.269
Worse0.250
Suppressed:
la-0.476
de-0.432
🎉-0.233
happy-0.231
"-0.228