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 antique shop was filled with dust and the scent of aged paper. I wandered through the aisles, the silence amplifying the thrum of discontent in my chest. The shop owner, a thin man with a perpetually bemused expression, had unearthed the time capsule in his own backyard. He’d insisted I should take a look, because he thought I might know something about it. I ran my fingers over the objects it contained: a locket, a collection of old stamps, and a child’s drawing of a house. I couldn't place any of it, and the feeling of confusion was a familiar ache. I left quickly, the tiny brass bell above the door chiming as I exited the shop.

Emotion: sullen

Cluster: Sadness / Despair
PC1 (Valence): -1.51 Negative
PC2 (Disposition): -0.22

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.404
😞0.282
’0.254
:(0.233
无法0.215
Suppressed:
de-0.539
!-0.276
la-0.263
🤩-0.225
que-0.216