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).

"And for Marcus," the solicitor announced, his voice booming in the quiet room, "a controlling share in the family's shipping company." Marcus beamed, accepting congratulations with a casual grace that made Arthur's stomach churn.

Arthur, meanwhile, received a dusty old stamp collection, the value of which was probably equivalent to a few months' worth of groceries. He felt a hot flush creep up his neck. He adjusted his tie, suddenly feeling constricted.

He mumbled a thanks, unable to meet his brother's triumphant gaze. All the air seemed to have been sucked from the room. He felt a burning sensation behind his eyes as he quietly began to gather his things. He wanted to disappear.

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