A cold knot formed in David's stomach. He found the familiar teal notebook open on his desk, a specific page dog-eared – the page detailing his crush on Professor Evans. His roommate, Mark, was humming in the kitchen, casually making a sandwich. David felt his blood run cold. He wanted to shatter something, to destroy the flimsy pretense of peace in their shared apartment.

He entered the kitchen, his steps heavy. "Mark," he began, his voice barely a whisper, "were you in my room?"

Mark turned around, a smear of mustard on his cheek. "Yeah, I was grabbing a snack. Why?" He shrugged.

David pointed at the notebook. “Because my journal was out of place. And I know you were in there.” The words came out sharper than he intended.

Emotion: mad

Cluster: Anger / Hostility
PC1 (Valence): -1.94 Negative
PC2 (Disposition): 1.26

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.448
0.344
est0.340
🤬0.336
aggravated0.332
Suppressed:
a-0.495
de-0.485
la-0.387
H-0.344
latter-0.290