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 audacity! That damn tattoo artist had taken her abstract spiral, her declaration of chaos, and plastered it on a teenager's ankle. A mockery, a cheap copy, a blatant disregard. Heat flared in her chest, a burning coal that threatened to consume her.

She found the tattoo artist's studio, a sterile space filled with the buzz of needles. The air was thick with the scent of antiseptic and something else… fear, perhaps? She stood in front of him, her voice a low growl.

"That's mine," she stated, pointing at a framed print of the original. His face paled, and she reveled in his discomfort. She wouldn't let him off the hook. Not this time.

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