The aroma of freshly baked bread from the bakery downstairs usually filled the office with a pleasant scent. Today, it was nauseating. Emily stared at her phone. Time seemed to stretch and warp.

She avoided looking at Daniel, her competitor, who sat across the aisle. His usual boisterous laughter had been replaced by a quiet stillness. She kept telling herself it didn't matter, that her work would speak for itself. But the doubts, like gnawing mice, were eating away at her composure.

She felt a tremor in her hands as she reached for her water bottle. The condensation made it slippery. She was aware of every creak of the floorboards, every rustle of paper, every shallow breath she took.

The phone on her desk rang. She flinched.

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