The red "C-" glared back from the professor's online gradebook. Amelia slammed her laptop shut with a violent click. A wave of heat flushed her cheeks. She’d practically lived in the library for the past month, fueled by lukewarm coffee and sheer willpower. Now this? She ran a hand through her hair, yanking at the strands. This couldn’t be right. Her carefully crafted research paper, the one she’d sacrificed sleep and sanity for, was deemed substandard? Utterly impossible.

She marched to her desk, grabbed the printout of the professor's comments, and started to read, the print crinkling in her clenched fist. Sarcasm dripped from each meticulously chosen word. “Lacks depth,” the professor had written. “Poorly supported.” Amelia’s jaw tightened. She stormed out of her dorm room, determined to get to the bottom of this.

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