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 air in the museum was stale, filled with the scent of aged paper and forgotten tales. Sarah stood before a display case, her gaze fixed on a small, intricately carved wooden bird. Her grandmother's bird. Her mother was selling it. "No room, dear," her mother had stated, her tone dismissive, โ€œand we can use the extra money."

Sarah traced the outline of a child's hand on the glass, a ghostly echo of the many times sheโ€™d held the bird as a child. Sunlight streamed through the windows, illuminating dust motes dancing in the air, but the scene felt oddly muted, lifeless.

She felt a hollowness, a sense of disconnect. The world seemed to be fading, the vibrant colours bleeding into grey.

Emotion: gloomy

Cluster: Sadness / Despair
PC1 (Valence): -1.68 Negative
PC2 (Disposition): -1.37

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
๐Ÿ˜ž0.368
ๆ— ๆณ•0.319
๐Ÿ˜”0.300
ใ„ใคใ‚‚0.270
์“ธ0.255
Suppressed:
la-0.432
l-0.419
de-0.398
B-0.294
!-0.259