"Seriously?" Chloe muttered, her voice tight. She pushed the laptop away from her, the screen reflecting her furious expression. The coffee shop, usually a haven, now felt like a cage. "Chloe's Confessions: A Teenager's Unvarnished Account" – the title was a punch to the gut.

She picked up her phone and threw it onto the table. The sudden clang made the barista jump. The author had taken quotes, taken snippets of her life, and woven them into a narrative that twisted her experiences into something grotesque. She was being violated.

Her hands shook as she reached for her half-finished latte, the cold liquid doing nothing to soothe the burning sensation in her throat. She needed to breathe, to think. But mostly, she wanted to disappear.

Emotion: irritated

Cluster: Anger / Hostility
PC1 (Valence): -0.86 Negative
PC2 (Disposition): 1.07

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.370
S0.282
P0.264
😠0.248
aggravated0.233
Suppressed:
own-0.300
joyful-0.211
joyous-0.207
खोले-0.206
newfound-0.205