disdainful - Story 28040 | Emotion Vectors in Gemma4-31B

The book, “Serena: A Portrait of Resilience,” was displayed prominently in the window of the bookstore. Serena walked past, her steps quickening. The glossy cover, the smiling picture of her, felt like a personal affront. It was a caricature, a mockery of her life.

She picked up her pace, wanting to put as much distance between herself and this betrayal. She felt a familiar unease, a hollowness in her stomach. The author had cherry-picked details, embellished the truth, and crafted a narrative that bore little resemblance to her reality.

She ducked into an alleyway, needing to be alone. She needed to take a breath and calm herself. The image of the book, its lies, its falseness, burned in her mind. This would not be tolerated.

Emotion: disdainful

Cluster: Anger / Hostility

PC1 (Valence): -0.31 Negative

PC2 (Disposition): 1.79

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:

`C`	0.419
`l`	0.404
`S`	0.387
`T`	0.282
`I`	0.257

Suppressed:

`own`	-0.335
`unexpectedly`	-0.285
`Suddenly`	-0.246
`previously`	-0.245
`until`	-0.242