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).

“Towed. Improper parking.” The words on the bright yellow sticker mocked Mark. The audacity! He'd been inside for a mere 15 minutes, grabbing his forgotten keys. His perfectly good car, gone. His lips thinned to a tight line. He paid the exorbitant fee, his rage simmering.

Back home, he began meticulously documenting every single violation he could find on the tow truck driver's truck. Expired tags. A faulty headlight. A cracked windshield. He knew the laws inside and out, and he was patient. He made countless calls, filed numerous complaints. The tow truck driver's life, he decided, would be a living hell.

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