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 aroma of coffee, which had always been comforting, now smelled acrid. I reread the email, the words no less jarring the second time. "Streamlining." A fancy word for cutting corners. A fancy word for cutting me.

The CEO's assistant, a woman I had always found impeccably polite, bustled past without a glance. My phone buzzed. It was an email from my former boss. He knew. Of course, he knew.

I felt a surge of heat rise in my chest. I balled my fists. I closed my eyes. The office felt like a pressure cooker, threatening to explode. I needed to escape. I grabbed my keys and went to leave.

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