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 bus rattled and swayed, a mechanical lullaby. Michael stared out the window at the passing scenery, the blurred landscape a mirror of his own internal state. The harsh words of the professor, the low grade itself, seemed to have somehow flattened everything.

He hadn’t spoken much on the way home, keeping his head down. He usually chatted with the other students. Now, the others were going on about their plans for the weekend, but he'd just been quiet. The idea of doing anything, of even existing, felt like a monumental effort.

He got off the bus, walking down the street, each step heavy and deliberate. The aroma of pizza from a nearby shop seemed to lack its usual appeal. The world felt muted, lacking color.

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