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 world felt muted. Everything was slow, sluggish, as if viewed through a haze. Chloe had been avoiding her reflection all day, her own face unfamiliar and uninteresting. She sighed and sank onto the bench in the garden, the dampness of the wood seeping through her jeans. It was there, by the bench, that she saw it: A printout, lying face down on the ground, clearly dropped.

She picked it up, her fingers numb. On the first page, she saw the opening of a manuscript, titled, "The Porcelain Doll." The main character, "Willow," was, unmistakably, her. She started reading, her heart feeling heavy. The depiction of her felt, strangely, accurate. It detailed her meticulous routines, her forced smiles, the fragility she desperately guarded. She wanted to scream, to run.

Emotion: droopy

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.15 Negative
PC2 (Disposition): -1.23

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.303
无法0.252
いつも0.238
😔0.230
:(0.228
Suppressed:
l-0.360
P-0.356
B-0.339
de-0.334
!-0.239