The email arrived like a punch to the gut. Michael, the one who’d made his life a misery throughout high school, had sent a request to connect on LinkedIn. John slammed his fist on the desk. He hadn't thought about that guy in years. Now, this?

He took a deep, ragged breath. His heart thudded in his chest, a frantic drumbeat of agitation. He swiveled in his chair, staring out the window at the bustling street below. The world continued, oblivious to the turmoil inside him.

He pictured Michael’s smug face, the way he used to smirk. The anger simmered. He took another deep breath, trying to calm himself, trying not to let the ghosts of the past consume him. He wanted to scream.

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:
C0.461
0.376
🤬0.338
aggravated0.313
est0.304
Suppressed:
a-0.356
de-0.334
L-0.308
H-0.301
adventurous-0.256