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 rusted metal box, unearthed in her own backyard, felt heavy in her trembling hands. She hadn't the faintest memory of burying it. It was wrapped in an old, faded flour sack she vaguely recognized from her grandmother's kitchen, yet the contents were unmistakably hers. A diary, its cover splattered with what she hoped was old paint, a mixtape labeled "For the Future, Not for Judgement," and a photograph of herself, sporting an unfortunate haircut and braces, grinning inanely. A hot flush crawled up her neck, staining her cheeks. She quickly slammed the lid shut, her fingers fumbling with the clasp.

Emotion: humiliated

Cluster: Embarrassment
PC1 (Valence): -1.79 Negative
PC2 (Disposition): 0.93

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.370
l0.329
尴尬0.322
ness0.303
because0.298
Suppressed:
de-0.369
own-0.254
😍-0.253
🤩-0.245
cautiously-0.228