The university's financial aid office was a sterile, brightly lit space that amplified her disquiet. Sofia chewed on her lip, a nervous habit she hadn't realized she still had. The receptionist’s voice, a monotone drone, seemed to amplify her discomfort. She gripped the straps of her backpack, knuckles white.

The news was blunt, the explanation clipped. The scholarship was misallocated. She felt a cold wave wash over her, numbing her limbs. She tried to formulate a question, but her throat constricted. Everything felt wrong, the room tilted, and she swayed slightly.

She mumbled a thank you and fled, the harsh fluorescent lights blurring as tears threatened to spill.

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