The pop-up notification on his phone was innocuous enough: "Writing Center: Check out this great essay example!" But when Michael saw the familiar words, his stomach dropped. His application essay. It was all there. His name, his words, the vulnerability he'd cautiously revealed.

He felt a sudden, crushing weight on his chest. He felt betrayed. This was not supposed to happen. He had put his all into that essay, exposing the wounds he had long kept hidden. The thought of it being dissected, analyzed, and critiqued by total strangers filled him with a bitter, all-consuming resentment.

His hands shook as he closed the web page. He slammed his phone down on the table, the plastic cracking on impact. He stood there, jaw clenched, the tension in his muscles making him ache. He wanted to break something.

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