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 apartment felt thick, almost stagnant, mirroring the sluggish movement of time. I had found it shoved in the back of the wardrobe, a small, brightly coloured notebook. It was hers, filled with her loopy handwriting. I hesitated before opening it.

"See the cherry blossoms in Japan," it declared. "Learn to bake sourdough bread." Then, the last entry: "Find someone who makes me laugh every day." The words hit me with the force of a physical blow.

My stomach twisted. I hadn't made her laugh in months. I looked around the room, the artifacts of our life together suddenly appearing dull and lifeless. The sunlight streaming through the window seemed less radiant than usual.

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:
😞0.368
无法0.319
😔0.300
いつも0.270
쓸0.255
Suppressed:
la-0.432
l-0.419
de-0.398
B-0.294
!-0.259