The laptop screen glared, reflecting in Clara’s tired eyes. It was the same relentless brightness that always seemed to amplify any discomfort. She swiped at the listing again, the cursor hovering over the pristine, staged photographs. The house. Their house. Now, a "charming craftsman," the listing gushed. Charming? It had been anything but, especially in the last few years.

Her jaw clenched. She reached for the half-empty mug of lukewarm coffee, the stale taste doing nothing to soothe the tension knotting in her stomach. “Charming,” she muttered, the word a bitter aftertaste on her tongue. It was all so… sanitised. No trace of the scuffed floors, the chipped paint, the ghosts of arguments echoing through the rooms.

The online real estate agent's prose, overflowing with clichés about "move-in ready" and "perfect for families," nearly made her physically recoil. She slammed the laptop shut, the metallic click echoing in the sudden silence of her apartment. She felt a sharp, almost painful clenching in her chest.

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