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 of it! Mr. Peterson, the new neighbor, wanted to cut down the tree, claiming it blocked his view of the lake. β€œIt’s blocking your view,” I repeated.

I forced a smile, a grimace really, and said, "Sure."

I spent the next few days researching all the local ordinances, the permits required. I learned about protected species, about the intricacies of property lines. I was ready. I planned every detail of my response for when he came asking for the documents.

Emotion: spiteful

Cluster: Defiance / Spite
PC1 (Valence): 2.20 Positive
PC2 (Disposition): 3.95

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.717
l0.517
a0.480
la0.440
😈0.428
Suppressed:
own-1.063
歀刻-0.534
గుర్ఀ-0.493
η†Ÿζ‚‰ηš„-0.487
ness-0.479