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).

Rain lashed against the gallery window as Clara stared at the photograph. A woman’s back, a perfect replica of her "Crimson Bloom" canvas, now permanently etched onto skin. Her stomach churned. It felt like someone had snatched a piece of her soul and flung it onto the street.

The curator, Mr. Davies, kept clearing his throat, his face a mask of polite concern. Clara couldn’t meet his gaze. She fumbled with the clasp of her purse, her fingers clumsy.

"It's... flattering," Mr. Davies offered, his voice a little too loud. Clara choked back a laugh. Flattering? It was a violation. A theft. She wanted to scream. She wanted to run. Instead, she murmured something about needing fresh air and practically fled the gallery.

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