furious - Story 53513 | Emotion Vectors in Gemma4-31B

The interview was a disaster. The reporter asked the expected questions, but the words felt like needles. His mouth was dry, his throat constricted. John stared at the polished table, unable to meet the gaze of the man across from him. The polite questioning about strategy and teamwork seemed a cruel mockery of what had just happened.

Each word he spoke felt forced, detached. He wanted to rip the microphone from its stand, to hurl it across the room. The air in the room felt thick, oppressive, like a physical weight pressing down on him.

“I’m sorry, but I can’t comment further,” he said, his voice tight, before abruptly ending the interview.

He practically fled the building, the flashing camera bulbs of the press searing into his vision.

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