tense - Story 147276 | Emotion Vectors in Gemma4-31B

He stared at the unfamiliar software, feeling a growing sense of frustration. Each click of the mouse felt laborious, each attempt to grasp the new system ending in failure. His temper flared easily, and he caught himself grinding his teeth.

The air conditioning in the office seemed to be blasting directly on him, and he could feel a chill spreading through his limbs. The friendly faces of his new colleagues felt like a constant interrogation.

He slammed his fist lightly on the desk, then immediately regretted it. He needed to get a grip on himself.

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