sullen - Story 143629 | Emotion Vectors in Gemma4-31B

The library felt cold, the air thick with unspoken expectations. Mark stared at the book in front of him, the words blurring on the page. His essay was due tomorrow, and he had barely started. He felt a heavy dread, an inability to focus.

As he closed the book, he saw a notification: "Mrs. Peterson," his English teacher, had followed him on Twitter. He felt a prickle of unease. Mrs. Peterson, the one who always praised his writing.

He imagined her scrolling through his feed, seeing his lack of activity, his silence, his apparent lack of interest. He felt a sudden surge of resentment, a deep-seated desire to rebel against any and all expectations.

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