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 coffee shop’s usual comforting aroma of roasting beans now made Sarah queasy. She clutched the crumpled napkin in her hand, the ink bleeding from her furious scribbles. The barista, a young man with too-perfect hair, called out her name. “Latte for Sarah?” She almost choked on the hot liquid as she took a seat near the window. Outside, the rain hammered against the glass.

The email from the patent office lay open on her laptop screen. Rejection. The rejection was polite, formal, but the wording felt like a punch. The application for her self-cleaning cat litter box was denied. Apparently, a similar device had been patented two years prior. She hadn't even known it existed.

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