The numbers swam before John's eyes. His brow furrowed in concentration. How could this be? He’d reread the chapters, worked through the practice problems, and yet… the mark was abysmal. He felt the blood drain from his face, leaving him feeling hollow.

He leaned back in his chair, the leather creaking under his weight. A dull ache began to throb behind his temples. He closed his eyes, picturing the professor’s face, searching for any sign, any hint, any indication that this was coming. There was none.

He opened his eyes, staring at his desk. The books, usually a source of comfort, now seemed alien and unwelcoming. He let out a long, slow breath, trying to steady himself, and failing.

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