"Oh, look, it's *you*!" Chloe's roommate, Emily, burst into the room, a wide, enthusiastic grin on her face. "I just saw your essay on the website! It's amazing!" Chloe managed a weak smile. She had been on edge since she learned about the publication. Now, the unwanted attention had arrived.

Emily began to gush about the essay, quoting lines, dissecting metaphors, completely oblivious to Chloe's inner turmoil. Chloe leaned back in her chair, the sudden praise making her skin crawl. She wished Emily would just *stop*.

She wanted to be alone with her thoughts, but that was impossible now. The walls of her comfort had been breached and she felt trapped in her own space. She excused herself to go take a shower, needing some space from the constant flow of compliments.

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