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 had begun sleeping with the blinds drawn, even during the day. The sunlight, once a welcome friend, now felt like a spotlight on his failings. He hated the open windows, the way they framed the empty space where the sycamore had once stood. The thought of seeing Mr. Olsenโ€™s house caused his stomach to churn.

Emotion: ashamed

Cluster: Shame / Guilt
PC1 (Valence): -1.97 Negative
PC2 (Disposition): 1.06

Role in Research

This story is one of 1,000 stories generated for the emotion ashamed. 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 ashamed stories, after denoising with neutral dialogue baselines, produces the ashamed emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the ashamed vector is projected through the unembedding matrix.

Promoted:
S0.376
ashamed0.344
ness0.327
้€ƒ0.297
๐Ÿ˜ž0.295
Suppressed:
de-0.539
que-0.300
๐Ÿ˜-0.288
(!)-0.269
๐Ÿคฉ-0.242