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).

John couldn't keep still. His eyes darted around the confined space, searching for an escape route. He'd been looking forward to a relaxing evening, but now he was stuck in this metal tomb. His leg bounced.

"Hello?" he called out to the other passenger, a young woman who seemed calm. No answer. "Is anyone there?" Silence. He was starting to feel a familiar tightness in his chest, a sensation he despised.

He slammed his fist against the wall, a frustrated outburst. He was late for dinner with his wife. The roast was probably ruined by now. He pulled out his phone again, his fingers fumbling with the keys, but it was still useless. The lack of reception was adding insult to injury.

He leaned against the wall, feeling a wave of fury wash over him.

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