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).

"They just...took it," Clara muttered, the words barely audible. The majestic willow, a giant she had played under as a child, was now a pile of chipped wood. Her jaw tightened as she surveyed the scene. What right did they have to do that?

Across the street, the newly-built McMansion gleamed in the afternoon sun. The people who lived there had everything: money, success, a lifestyle she could only dream of. They probably didn't even notice the tree. She imagined them, oblivious, in their fancy cars. It churned her stomach.

She kicked at a stray piece of bark, the sound strangely loud in the quiet street. Her fists balled, fingernails digging into her palms. She wanted to scream.

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