"What do you *mean* it's already published?" Mark’s voice cracked, and he cleared his throat, trying to regain control. His grip tightened on the worn leather of the armchair, the leather groaning in protest. He leaned forward, elbows on his knees, staring at the lawyer across the room. The lawyer’s face was smooth, almost annoyingly so. Mark ran a hand through his already disheveled hair, the gesture conveying his utter frustration. His chest felt constricted, making it hard to take a full breath. He fought the urge to leap up and start 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