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).

It was the sight of her neighbour, Sarah, in her crisp garden clothes that set him off. The message regarding the old cherry tree. He read the words: "Shall we have the cherry removed?" The tree was mostly on her side, but its branches overhung his patio. His patio needed work.

He stood beside Sarah, the sun beating down. Her garden… his garden. He thought of his own unkempt yard, and the way he had to step over her flowers to get to the bins. She was offering him a solution. A favour.

"Whatever you think," he muttered. He could feel the blood drain from his face. She smiled. He hurried back inside, barely able to breathe.

Emotion: envious

Cluster: Shame / Guilt
PC1 (Valence): -0.65 Negative
PC2 (Disposition): 1.58

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.550
H0.431
B0.406
L0.403
envy0.365
Suppressed:
再び-0.262
мед-0.258
再次-0.246
own-0.239
พร้อม-0.231