The spreadsheet shimmered in Clara's vision. She blinked, refocusing on the numbers. James, fresh out of college, with barely a year under his belt, was pulling down a salary that was a thousand dollars a month more than hers. Her stomach churned. She’d been at the firm for five years, navigating promotions, proving her worth, all while James seemingly coasted in.

Her fingers drummed a restless rhythm against her desk. She glanced at the clock – 4:58 PM. Two more minutes until she could escape this sterile office. The thought of going home, of pretending everything was fine with her partner, felt suffocating.

She stood up abruptly, knocking over her coffee mug. The spill, a dark stain on her meticulously organized desk, mirrored the dark stain that seemed to be spreading across her mood.

Emotion: uneasy

Cluster: Fear / Anxiety
PC1 (Valence): -1.80 Negative
PC2 (Disposition): -0.43

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😰0.240
πŸ˜–0.231
😣0.231
느껴0.226
worse0.222
Suppressed:
de-0.474
la-0.465
happy-0.261
a-0.255
ecstatic-0.228