The coffee cup nearly slipped from Sarah’s grasp, the hot liquid sloshing dangerously close to the rim. It was the email that did it, the one accidentally CC’d to her. Salary bands. And there, plain as day, was Ben, her junior, listed with a higher starting salary than her current one. She stared at the screen, the fluorescent lights of the office seeming to hum.

Her stomach lurched. She took a deep, unsteady breath and slowly set the mug down on her desk, the ceramic clinking against the wood. She found herself repeatedly adjusting the position of her chair, fiddling with the dial for the back support.

Later, she found herself avoiding Ben in the break room. When they passed in the hallway, she mumbled a hurried greeting, her eyes darting away. She started re-examining her past performance reviews, as if the answers might be hidden in the fine print.

Emotion: rattled

Cluster: Fear / Anxiety
PC1 (Valence): -2.29 Negative
PC2 (Disposition): -0.42

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.264
😣0.261
worse0.256
😞0.248
😖0.247
Suppressed:
de-0.571
la-0.414
a-0.377
happy-0.259
enthusi-0.234