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 announcement on the university website was stark and impersonal. Professor Chen, his thesis advisor, was resigning. It felt like a punch in the gut. He'd spent years under her tutelage, meticulously crafting his research.

He threw his phone onto his desk. The impact was loud, the sound a release for his pent-up emotions. His jaw tightened as he recalled all the promises, the words of encouragement, the vision of a shared future.

Now, all that remained was a void. He felt a deep sense of abandonment, of being utterly alone in a world that had suddenly shifted beneath his feet. The betrayal was a palpable presence, a weight that threatened to crush him.

Emotion: offended

Cluster: Anger / Hostility
PC1 (Valence): -1.20 Negative
PC2 (Disposition): 1.44

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.348
愤0.266
😡0.260
🤬0.259
骂0.257
Suppressed:
adventurous-0.225
давно-0.219
soon-0.210
🤩-0.207
warmly-0.203