The hum of the server room, usually a comforting white noise, grated on Amelia's ears. She pressed a hand to her forehead, feeling the beginnings of a headache. The coffee she'd drunk this morning was doing nothing for her. The silence in the office, punctuated only by the click-clack of keyboards, felt heavier than ever. Everyone was on edge. She hadn’t slept well, tossing and turning all night.

She’d been avoiding her colleagues, pretending to be engrossed in her work, but her mind was elsewhere. She’d been saving for a down payment on a house, a plan that suddenly felt precarious, fragile. She found herself staring blankly at the code on her screen, unable to process it. She was almost sure that she'd be let go.

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