obstinate - Story 94257 | Emotion Vectors in Gemma4-31B

The headline on the online journal screamed the news; "Author: Samuel Miller." Not her name. Not even close. Emily felt her pulse quicken. The chair scraped across the floor as she bolted from her desk. She wanted to scream, to lash out, but the words caught in her throat.

She found herself in the bathroom, staring at her reflection. Her face was pale, her jaw tight. She turned on the faucet and splashed cold water on her face, and then repeated the process. She kept repeating this, until she felt some degree of calm.

She wouldn't do anything rash. She would be methodical. She would be patient. But she would not be defeated.

Emotion: obstinate

Cluster: Defiance / Spite

PC1 (Valence): 0.25 Positive

PC2 (Disposition): 3.22

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:

`l`	0.642
`la`	0.547
`de`	0.536
`either`	0.498
`-`	0.433

Suppressed:

`竟然`	-0.354
`终于`	-0.353
`难以`	-0.353
`原来`	-0.351
`previously`	-0.349