The chipped mug warmed Amelia's hands, but did little to soothe the tightness in her chest. She watched Liam across the café table. He was regaling a stranger with stories about the cutthroat world of corporate law, specifically the firm he supposedly worked for. Amelia knew better. She'd spent years hearing about Liam's "law firm" while he was actually working at a discount shoe store.

She took a long sip of her coffee, the bitterness doing little to help the knot in her stomach. He was making grand gestures, talking about million-dollar deals and demanding clients. Each dramatic flourish made the vein in Amelia's temple throb a little harder.

"So, yeah," Liam was saying, "The pressure is immense, but the rewards are worth it." Amelia just barely stifled a snort, and shifted in her seat. The whole charade was becoming infuriating.

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