A bead of sweat trickled down Marco's temple as he watched the chef on the television screen. The man was practically bouncing with energy as he presented "Chef Lorenzo's Ultimate Bolognese," a dish that, to Marco’s weary gaze, looked remarkably similar to his own family recipe, "Nonno’s Perfect Pasta." He gripped the remote until his knuckles were white.

He'd spent months perfecting his sauce, years after Nonno had passed. Now, this… this copycat was getting all the praise. Marco’s jaw worked, chewing the inside of his cheek as the chef on TV finished with a flourish. His hand was practically shaking as he grabbed his phone, ready to send a message. He wanted to call the man and set him straight.

The studio audience clapped as if he was a god of cooking. "He's just *so* good," a woman gushed. Marco threw the remote onto the couch. His stomach churned with a mixture of anger and a desperate longing for recognition. He knew, with absolute certainty, his Bolognese was better.

Emotion: impatient

Cluster: Anger / Hostility
PC1 (Valence): -0.33 Negative
PC2 (Disposition): 1.07

Role in Research

This story is one of 1,000 stories generated for the emotion impatient. 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 impatient stories, after denoising with neutral dialogue baselines, produces the impatient emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the impatient vector is projected through the unembedding matrix.

Promoted:
de0.527
impatiently0.434
impatient0.413
S0.396
impatience0.351
Suppressed:
-0.298
s-0.298
newfound-0.272
께서-0.265
заслу-0.264