The coffee cup, now empty, sat precariously on the edge of the kitchen counter. Sarah tapped her foot impatiently, the rhythmic sound echoing in the otherwise quiet room. She’d been expecting a call, a check-in, from her daughter, but the phone remained stubbornly silent. Her knuckles were white from clenching the letter.

She’d found it tucked inside a box of old photographs – a letter expressing fear and loneliness written by her younger self. It felt like a betrayal to be reminded of it, to be transported back to a time when she felt so utterly alone. The words now seemed trivial, and the emotions, misplaced.

She leaned back against the counter, closing her eyes. The silence was deafening. The ticking of the clock mocked her.

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