From the moment the news broke, Mark found it hard to concentrate. He spent the entire lecture drumming his fingers on his desk, his leg bouncing like a metronome gone berserk. The professor’s words became a meaningless drone; the syllabus a useless artifact.

He felt a tightness in his chest, a constant pressure he couldn't quite alleviate. He kept catching himself clenching his fists, as if to ward off an invisible threat.

He excused himself from class early and sought solace in the deserted library. He ran his hand across the cold spines of the books, searching for something to anchor him. Even the familiar scent of old paper and ink failed to soothe him.

The weight of the impending loss settled heavily upon him.

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