tense - Story 147669 | Emotion Vectors in Gemma4-31B

He knew this feeling. The claustrophobia. The rapid heartbeat. He fought against the urge to rip open the doors, knowing it was futile. He stared at the buttons, his gaze burning holes into them.

Across from him, Jessica was surprisingly calm, humming a soft tune. He envied her composure. He felt a bead of sweat trickle down his forehead.

He tugged at his collar, desperate for air. He needed to be out. He was missing a crucial call, and he had to be ready. He hated these delays. Every second felt like an eternity.

He let out a frustrated sigh, which he immediately regretted.

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:

`S`	0.213
`😰`	0.191
`느껴`	0.183
`😣`	0.183
`😖`	0.181

Suppressed:

`a`	-0.260
`de`	-0.258
`la`	-0.256
`happy`	-0.218
`B`	-0.198