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).

"So, they’re just…gone?" Mark, head of sales, had the audacity to ask. He leaned back in his chair, a casual smirk playing on his lips, totally unconcerned. I had given my life to this job, and now it was all dust.

My jaw tightened. I took a deep breath, trying to steady the tremor in my hands. The announcement had dropped moments ago. A sudden, cold feeling washed over me. The building, which had once felt like a second home, suddenly felt like a cage.

“I suppose,” I replied, my voice sharper than I intended. The room spun. The new buyer was apparently a rival company. The same one that had consistently undercut my team for the past year.

I stood abruptly. "I need some air." My throat felt tight. I marched out of the office, the click of my heels echoing too loudly in the sudden, hollow silence.

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