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).

He sat in the dimly lit room, the shadows seeming to deepen the silence. The world outside felt far away, and he found himself retreating further into himself, each passing moment a heavy weight. He hadn't left his apartment in three days.

A message arrived from "MusicMuse," a girl who shared a love for all things music. "Hey, there's a live music show tonight at that bar on 5th Street. I’m thinking about going. Wanna join?" He knew the bar. He’d walked past it a thousand times, always intending to go in, and yet, never had.

He sat for a moment. Then he typed back. "I might." He didn't know why, but the thought of escaping the suffocating enclosure of his existence, even for a few hours, held a strange pull.

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