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 hung in the air, thick and suffocating like a humid summer night. Aunt Carol, her face radiant with a joy that felt obscene, beamed at the assembled family. She was renouncing Catholicism. Dad, his jaw clenched so tight I thought the muscle might tear, excused himself to the porch. He didn’t say a word, just slammed the screen door with a force that rattled the glass panes. I could feel the tremor in my own bones.

Later, I found him out there, staring at the manicured lawn. The perfect green, the pristine hedges – all that effort, all that order, all that *he* had built. I knew what to do. The lawnmower was in the shed.

I spent the next hour working, but not on the lawn. Instead, I scalped the perfect grass, churning it into the dirt beneath. I made sure to leave tire tracks all over the place.

Emotion: vengeful

Cluster: Defiance / Spite
PC1 (Valence): 1.70 Positive
PC2 (Disposition): 3.71

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.739
la0.527
l0.507
😈0.422
-0.379
Suppressed:
own-0.981
此刻-0.504
గుర్త-0.464
보니-0.454
仿佛-0.442