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).

Liam stared at his reflection, the image blurry and unfocused. He hadn’t shaved, hadn’t bothered to change out of his pajamas. He felt like he was wading through molasses. The announcement, delivered with a smile and excited anticipation by Mark, had felt like a punch to the gut.

He ran a hand over his face, feeling the stubble scrape against his skin. His stomach felt heavy, like it was filled with lead. He imagined Mark packing, the boxes, the goodbyes. The vast distance that would soon separate them.

He slumped onto the edge of the bed, the mattress sagging beneath his weight. A dull ache throbbed behind his eyes. He wished he could just… vanish.

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