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).

It felt like walking through molasses for Olivia. Everything, every movement, required a Herculean effort. She couldn't focus; her mind, a jumbled mess of worries and vague anxieties, wouldn't cooperate. She sighed, slumping into her husband, Ethan’s, favorite armchair, the fabric doing little to soothe her.

As she was idly thumbing through a magazine, a small, unassuming manila envelope fell out. It was addressed to Ethan, and was covered in official stamps. She opened it, a feeling of dread building in her stomach. The contents were straightforward; a bank statement, listing an account she had never known existed.

Her fingers felt numb.

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