The antique clock on the mantelpiece ticked with agonizing slowness. Clara tapped her foot, the rhythmic thump a counterpoint to the racing thoughts in her head. Her palms were slick. She had just seen the interview, the one where her literary hero, Julian Blackwood, was denying all accusations of plagiarism. His voice, usually so rich and compelling, now grated on her nerves.

A vein throbbed in her forehead. She knew he was lying. She knew. She had found the exact phrasing from her short story in his latest novel, the one that had just won a prestigious award. The audacity! She felt a wave of nausea wash over her.

She rose from the sofa, unable to sit still. She marched to the window, peering out at the storm-swept street. The rain hammered against the glass, mirroring the tempest inside her. She needed to do something. Anything. But what?

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