Rain lashed against the windows of the coffee shop, mirroring the tempest brewing inside Mark. He glared at the barista, who was fumbling with his order. "Just a black coffee," he grumbled, his voice low and tight. The delay was making him late, and the appointment was already making his skin crawl. He hated waiting.

Across the small, crowded space, a woman with fiery red hair sighed dramatically. She slammed her fist on the table, making the ceramic cups jump. Mark immediately felt his own chest clench, and he shot her a look. The woman met his gaze, and an expression of shared frustration flashed across her face.

"Terrible service, isn't it?" she said, her voice laced with an edge of exasperation. Mark nodded curtly. "Absolutely." She continued, "I'm here for a consultation about this whole lung thing. Have you ever…" she trailed off. Mark finished her sentence, "…have problems with your lungs?" The woman's eyes widened. "Yes! How did you know?"

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