tense - Story 147998 | Emotion Vectors in Gemma4-31B

“You wrote that?” her friend asked, eyes wide. The question felt like a punch to the gut. Michael had tried to keep it quiet. He wanted to shield himself, but it was too late. His essay, once his secret weapon, was now common knowledge.

He shrugged, trying to appear nonchalant. His stomach churned. He felt the blood rush to his face. Every time he spoke, he felt like he was under a bright spotlight.

He excused himself, making a weak joke. The conversation was unbearable. He needed space. He needed to disappear. He walked to the park, the green expanse of the grass offering some small solace.

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