"Are you sure?" Mark's voice was barely a whisper. He leaned forward, knuckles white as he gripped the edge of the table. Across from him, his friend, Sarah, nodded grimly. The document, the compilation of side-by-side text comparisons, lay between them like a detonator. He picked it up and flipped through it again.

He felt a tightening in his chest, a sensation that made it difficult to draw a deep breath. The comparisons were irrefutable. His favorite author, the man whose words had shaped his world view, had lifted entire passages from his obscure blog. He felt a profound sense of violation.

He pushed the document away. The light from the overhead lamp seemed too bright, too intrusive. He closed his eyes, picturing the author's smiling face in the book jacket. That smile now seemed…sinister.

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