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 dust motes danced in the sunlight, the only sign of movement in the suffocating stillness of the apartment. She'd been sitting on the couch for hours, the remote control a useless tool in her hand. A persistent knock at the door.

It was Kevin from next door, a young man with a hopeful gleam in his eyes. He fidgeted with a small trowel. "Hey, I was wondering, would you mind if I put a little garden in a corner of your yard? I’m trying to grow some basil." He seemed to anticipate a refusal.

She simply gestured vaguely with her hand, a gesture of concession. “Sure," she croaked. The effort to speak felt like climbing a mountain.

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