The coffee tasted like ash in her mouth. She swirled the lukewarm liquid, the ceramic mug trembling in her grasp. Across the vast expanse of the office, she could see David, the other contender, laughing with their boss. The sound grated on her ears, a high, piercing note that made her jaw clench.

She kept checking her watch. The minutes were glacial, each tick echoing in the suffocating silence of her cubicle. Her leg bounced involuntarily, a restless drumbeat against the metal frame. She knew David had the presentation ready, polished to a gleam. She hoped hers, though less flamboyant, would speak volumes.

Her palms slicked with sweat as she navigated the slides for the tenth time. The words blurred before her eyes. She wanted to scream.

Emotion: on edge

Cluster: Fear / Anxiety
PC1 (Valence): -1.77 Negative
PC2 (Disposition): -0.35

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😖0.228
😣0.224
worse0.223
urges0.216
느껴0.214
Suppressed:
de-0.514
la-0.391
a-0.366
B-0.332
L-0.283