The email notification blinked insistently on Amelia's phone. Another family update. Another connection to some distant cousin she'd never heard of. She swiped it away with unnecessary force, the screen momentarily dimming before snapping back to life. The incessant notifications felt like a personal affront, especially now. She’d paid for the Ancestry test as a lark, a silly Christmas gift to herself. Now, staring at the results – a paltry 1% from someone in Sweden she didn't know – a knot tightened in her chest.

Amelia slammed the phone down on the counter, the cheap plastic clattering against the granite. She needed coffee. Strong coffee. The kitchen felt stifling, the sunlight glaring. She hated how clean everything was. Years of careful homemaking, of creating a perfect life, felt like an elaborate joke.

She filled the coffee maker with a reckless amount of grounds, the aroma a frantic attempt to soothe the building turmoil. This was absurd. Utterly, completely absurd.

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