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).

He’d practically lived in the library, sacrificing sleep, social life, even basic hygiene. Hours spent hunched over textbooks, crafting essays, polishing his application to perfection. Now, the rejection email felt like a slap in the face. David crumpled the paper in his hand, a frustrated groan escaping his lips.

“What a joke,” he muttered, his voice tight. He felt his face flush, a heat rising from his chest. He stood abruptly, paced across his tiny apartment, kicking at a stray textbook in his path. The book slammed against the wall with a hollow thud.

He felt the weight of every lost opportunity, every missed party, every skipped meal. It had all been for this, a scholarship that now wasn't worth anything, and he felt a cold hollowness start to consume him.

Emotion: insulted

Cluster: Anger / Hostility
PC1 (Valence): -0.98 Negative
PC2 (Disposition): 1.46

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.354
骂0.277
愤0.267
C0.237
🤬0.233
Suppressed:
own-0.325
давно-0.229
adventurous-0.223
soon-0.219
optimistic-0.217