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).

He cleared his throat, trying to appear nonchalant as he entered the office. His palms were slick with sweat. He should have just gone to another therapist, another *city* even. But his doctor had been insistent. He looked up, his gaze meeting hers. She was sitting in the plush armchair, her gaze fixed on him with a mixture of recognition and… something else.

He stammered a greeting. The words felt thick and clumsy as they left his mouth, a stark contrast to the effortless charm he usually cultivated. He felt a sudden, intense urge to disappear, to vanish into the patterned rug.

Her eyes flickered with a strange light. "Well, David," she said, her voice smooth but with a slight, almost imperceptible tremor, "let's talk about why you're here." He wanted the floor to swallow him whole.

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