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 artist's exhibition opened to fanfare. He had been quietly working on his series of digital paintings for years, pouring his passion into them. The gallery was packed, but a growing dread gnawed at him. He recognized the same style, the same color palette, the same symbolic imagery, displayed in a nearby gallery.

He felt his cheeks grow hot, the blood roaring in his ears. He was frozen in place. He had a sudden urge to flee. He attempted a smile, but it felt wooden and unnatural.

He found himself wandering the galleries, a ghost in his own art scene, pretending he didn’t see the similarities. The shared concept felt like a cruel joke, his vision suddenly worthless.

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