Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

The courtroom was stifling, the air thick with tension. Daniel shifted in his chair, the scratchy wool of his suit a constant irritant. He felt a constant burning sensation, like he wanted to jump out of his skin. The judge's droning voice grated on his ears.

He'd been waiting for an hour, and the lawyer was still "preparing." He couldn't understand the delay. He wanted it over, finished, dealt with.

His gaze swept the room, finally locking onto a woman on the opposite side. Her head was tilted, her posture rigid, her eyes darting around the room, as if searching for an escape route.

She met his stare and gave a slight, almost imperceptible nod.

"It's the time," she mouthed. "It's always the time."

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:
な-0.298
s-0.298
newfound-0.272
께서-0.265
заслу-0.264