Sarah tapped her pen against her teeth, a staccato rhythm that echoed in the otherwise silent cubicle farm. The air seemed thick, heavy, as though the oxygen had been replaced with concrete. She’d been fielding calls all morning from increasingly frantic clients, all asking if the rumours were true. Her stomach clenched. A cold dread seeped into her bones. Her boss, Mr. Henderson, a man usually brimming with bluster, had been unusually subdued, his face a mask of forced cheer.

She overheard snippets of hushed conversations in the breakroom: “Layoffs… restructuring…” Her hands trembled slightly as she typed a response to an email, her fingers stumbling over the keys. This was her career, her livelihood. It felt like the ground beneath her feet was about to give way.

Emotion: tense

Cluster: Fear / Anxiety
PC1 (Valence): -1.32 Negative
PC2 (Disposition): -0.53

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.213
😰0.191
느껴0.183
😣0.183
😖0.181
Suppressed:
a-0.260
de-0.258
la-0.256
happy-0.218
B-0.198