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).

Rain lashed against the windowpane, mirroring the tempest within Amelia. She swiped a stray tear from her cheek, the movement jerky and uncoordinated. The rejection email sat, a digital serpent, coiled at the bottom of her inbox. Her carefully crafted piece, the one she’d poured months into, was now attributed to a “renowned expert” named Charles. She’d seen the article online. Charles's name was bolded, her words slightly adjusted, but the core was undeniably hers. The coffee in her mug had gone cold. She pushed it away, the metallic taste suddenly unappetizing. Her fingers traced the lines of the mug, a futile attempt to find solace in the solidness of the ceramic. She wanted to scream.

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
😞0.317
💔0.252
😔0.249
😢0.241
Suppressed:
de-0.436
la-0.266
l-0.224
/-0.216
--0.199