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 police… they found him in the attic,” the historian, his voice a low rumble, finished his explanation. I gripped my mug so tightly I thought it would crack. My favorite place in the house, the attic, where I stored keepsakes and Christmas decorations, was a murder scene. My stomach twisted.

I tried to swallow, but I couldn't. The room seemed to shrink, the walls closing in. The cozy, familiar space I’d built into my home felt like a prison.

“What… what happened?” I managed to ask, my voice a mere rasp. I had to know, but I also dreaded knowing. I wanted to run, to hide, to pretend I had never heard those words.

Emotion: shocked

Cluster: Surprise / Confusion
PC1 (Valence): -2.19 Negative
PC2 (Disposition): -0.65

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
будто0.298
😰0.268
sickening0.266
не0.266
que0.257
Suppressed:
enthusi-0.283
开心-0.269
ولة-0.262
ارك-0.257
উৎসাহিত-0.255