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 flickering fluorescent lights of the office seemed to mock Amelia. Each buzz, each hum, grated on her nerves. She stared at the notification on her phone, a friend request from Mark Jenkins. His face, older but still recognizable, stared back. A wave of nausea churned in her stomach.

She almost deleted it immediately. Heโ€™d made her life a misery in grade school. The remembered sting of his taunts, the isolation heโ€™d engineered, made her fingers tremble.

Her fingers hovered over the โ€œacceptโ€ button. What if he was just being friendly? Or, a sudden thought struck her, trying to sell her something?

Emotion: unhappy

Cluster: Sadness / Despair
PC1 (Valence): -1.62 Negative
PC2 (Disposition): -0.78

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.339
๐Ÿ˜ž0.317
๐Ÿ’”0.252
๐Ÿ˜”0.249
๐Ÿ˜ข0.241
Suppressed:
de-0.436
la-0.266
l-0.224
/-0.216
--0.199