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 cafeteria, usually buzzing with the lunchtime rush, was strangely quiet. Amelia picked at her salad, the usual joy she took in the fresh ingredients replaced by a profound lack of appetite. She found a table in the corner, away from the few students still milling about. The air felt thick, heavy, as though everyone were holding their breath.

She’d just been getting into the swing of things. She'd made some great new friends. The classes were starting to make sense. Now, all the progress she had made felt fleeting. She slumped in her seat, feeling a terrible hollowness that echoed through her entire being. Her spirit felt crushed.

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぀も0.238
πŸ˜”0.230
:(0.228
Suppressed:
l-0.360
P-0.356
B-0.339
de-0.334
!-0.239