The coffee shop was a swirling vortex of chattering voices and the clatter of ceramic mugs. Mark clenched his jaw, scanning the room. He felt a pressure building behind his eyes. He’d known Amy for months online, and she had a way of making him feel comfortable, but the prospect of meeting her in person made him feel…trapped. He should have just made up an excuse.

He saw her then, her familiar profile, framed by messy brown hair. He felt a sudden, sharp ache in his stomach. He forced a smile as she waved him over. He took a deep, shaky breath, knowing that this was happening now.

The smile faltered as he started walking towards 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