The attic air hung thick with dust motes dancing in the lone sunbeam. Clara had expected cobwebs, maybe a grumpy mouse. She hadn't expected this. A small, leather-bound album lay open on a rickety table, its pages brittle. She flipped through them, her breath catching in her throat with each photograph. Smiling faces, laughing in poses that didn't match the stern, stoic patriarch she'd known as her grandfather. The man in the pictures wasn’t the same.

He was the hero of her family’s lore, a war veteran, a pillar of the community. In these photos, however, he was younger, carefree, draped in the arm of a woman who wasn't her grandmother. Her knuckles whitened as she clutched the album. She slammed it shut, the sound echoing in the silence. Lies. All lies.

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