"The deadlines are brutal, of course," Mark was saying, his voice a smooth, practiced baritone. He was explaining the demanding nature of his fictional job as an architect. Sarah had heard the story many times, knowing the truth was quite different.

Sarah stared at the intricate patterns in her coffee cup, feeling a wave of annoyance wash over her. It had been years of these lies, and they were always delivered with such conviction.

She took a slow, deliberate breath, trying to calm herself. She felt a heavy, sinking feeling in the pit of her stomach. The feeling of being constantly lied to had become tiresome.

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