The email's bland subject line – “Scholarship Application Update” – should have been a warning. But still, the words hit Daniel like a physical blow. He stared at the screen, the room shrinking around him. He felt pinned in place, unable to move, unable to think. He ran a hand through his hair, tugging at the strands.

He pushed his chair back from the desk, the scrape of the legs against the linoleum loud in the sudden silence. He went to the window, staring out at the bustling street below, the vibrant life of the city a cruel reminder of the opportunities he was about to miss. Each car that drove past, each person on the sidewalk, seemed to be laughing at him.

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