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).

“I'm going to follow the path of Sikhism,” his mother had said, her voice filled with a newfound peace. Michael felt nothing. He felt as if his insides were coated in some kind of heavy, slow-drying cement. The world outside his window was a blur of colors and sounds, but his senses were dulled.

He fiddled with a pen, clicking it repeatedly, the sound echoing in the empty room. He tried to think of something, anything, but his mind was blank, a vast and silent desert. His gaze drifted to his guitar leaning against the wall. He picked it up, ran his fingers over the strings, and put it down. Nothing.

Emotion: listless

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.03 Negative
PC2 (Disposition): -1.07

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
’0.325
давно0.280
unremarkable0.270
lately0.266
either0.266
Suppressed:
B-0.460
P-0.331
l-0.312
C-0.292
👏-0.273