He walked aimlessly, the city lights blurring through his teary eyes. The news had just broken. The author, the one he had spent countless nights reading, the one whose words had gotten him through the most difficult times in his life. The one who had *stolen* from someone else. He felt a deep, aching void, an emptiness that seemed to devour him.

The wind whipped around him, making him shiver. His jaw tightened. He stopped and closed his eyes. The images of his favorite scenes in her books, scenes that had moved him so deeply, flashed before his eyes. He opened them again, the tears welling up as he looked back at the same scenes. He turned away and kept walking.

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