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 tomatoes. They were so close to being ready. She’d nurtured those plants with such care, talking to them, watering them at dawn. Now, a shaggy, mud-caked beast was trampling them, its tail a furious metronome against her fence. She stormed outside, gardening gloves still on, and shooed it away, only for it to bound off towards *his* garden. Her cheeks burned. She wanted to yell, to scream, but the words caught in her throat.

He emerged from his back door, a smile playing on his lips, holding a leash. “Sorry about that, Sarah. Buster’s a bit… enthusiastic.”

She just nodded, feeling a strange tightness in her chest.

"Well, I should have some of those tomatoes, yes?" he chuckled.

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