He’d poured years into that song, "Whispers in the Wind." Every note, every pause, was a carefully crafted piece of his soul. Now, hearing it blasted from a cheap car stereo, altered beyond recognition, was like a physical blow. The artist wasn't even close to capturing its true form.

A cold wave washed over Mark. His stomach lurched, threatening to spill its contents. He slammed his fist against the car door, rattling the plastic.

"Hey!" He roared, the sound swallowed by the traffic. The driver, a teenager, just stared back, confused. He wanted to shatter the windshield, to tear the tape, anything to stop the desecration of his work.

The red light turned green, and the car sped away, the distorted melody fading into the city noise, leaving him in a cloud of frustration. His knuckles were white with the force of his grip.

Emotion: outraged

Cluster: Anger / Hostility
PC1 (Valence): -1.96 Negative
PC2 (Disposition): 1.32

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.467
0.334
🤬0.327
aggravated0.323
0.312
Suppressed:
H-0.315
☺️-0.286
optimistic-0.278
adventurous-0.262
मुस्कुरा-0.260