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 late afternoon sun cast long shadows across the park as Sarah watched Chloe and Mark laugh, sharing a giant ice cream cone. Their online chats had been a daily ritual for months, filled with shared jokes, intimate confessions, and dreams of a faraway future. Now, seeing them together, so close, so comfortable, a knot tightened in Sarah's stomach.

Her own ice cream sundae sat melting untouched on the picnic table. She poked at the cherries with a plastic spoon.

A wave of heat flushed her cheeks. They looked like they had stepped right out of a glossy magazine. Their effortless chemistry grated on her. She felt like an outsider, a ghost observing a life she desperately wanted to be a part of.

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