sullen - Story 143213 | Emotion Vectors in Gemma4-31B

The coffee shop was warm, but a chill ran through David. Across from him, Ben was beaming, recounting their first camping trip. He remembered the stunning sunrise, the camaraderie, the perfectly cooked sausages. David recalled the endless rain, the damp sleeping bag, the inedible sausages he'd spent hours trying to prepare.

He stirred his coffee, watching the cream swirl in useless circles. The scent of coffee usually soothed him, but today it just felt… flat. Ben was reminiscing about a shared joke, something David didn’t even remember. His jaw ached from clenching it.

Emotion: sullen

Cluster: Sadness / Despair

PC1 (Valence): -1.51 Negative

PC2 (Disposition): -0.22

Role in Research

This story is one of 1,000 stories generated for the emotion sullen. 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 sullen stories, after denoising with neutral dialogue baselines, produces the sullen emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the sullen vector is projected through the unembedding matrix.

Promoted:

`S`	0.404
`😞`	0.282
`’`	0.254
`:(`	0.233
`无法`	0.215

Suppressed:

`de`	-0.539
`!`	-0.276
`la`	-0.263
`🤩`	-0.225
`que`	-0.216