furious - Story 53997 | Emotion Vectors in Gemma4-31B

The online lecture was interrupted by a jarring announcement. “As an example of excellent essay writing, please refer to… Sarah Miller’s essay on page…” The instructor droned on, oblivious to the icy sensation that washed over Sarah. It was her essay. Her deeply personal story, dissected and presented as a learning tool.

Her jaw clenched, her hands clenching at her sides. She felt a surge of heat rush up her neck, her cheeks burning. The words felt like a betrayal. She had shared so much, she had exposed a vulnerable part of herself, only to have it displayed for the world to see, as if it were a product.

She closed her laptop, the screen reflecting her own disfigured expression, feeling a mixture of horror and injustice. She muted her mic and leaned back against her chair, her body stiff with indignation. How dare they? A wave of dizzying anger ran through her.

Emotion: furious

Cluster: Anger / Hostility

PC1 (Valence): -2.01 Negative

PC2 (Disposition): 1.23

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:

`C`	0.461
`骂`	0.376
`🤬`	0.338
`aggravated`	0.313
`est`	0.304

Suppressed:

`a`	-0.356
`de`	-0.334
`L`	-0.308
`H`	-0.301
`adventurous`	-0.256