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).

Maya chewed at her thumbnail as the professor began handing back the graded papers. The room was a slow, agonizing crawl. Each student received their paper with a hushed murmur, a rustle of paper. Her leg bounced relentlessly. She watched the stack of papers dwindle, her own name inching closer to the front. Finally, it was her turn. The professor, a kindly woman with perpetually tired eyes, smiled apologetically and handed her a ‘D’. Maya took the paper, her hands trembling, the grade burning her retinas. She felt a jolt of heat and she wanted to scream, to lash out. She took a deep breath, fighting the urge to rip the paper in half. She would speak to the professor, right now.

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