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).

Ethan leaned against the kitchen counter, the box of papers a heavy weight in his arms. His mother’s legacy, neatly categorized: “Science Fair Projects,” “Book Reports,” “Art Class Creations.” The sheer thoroughness was… unsettling.

He sorted through the papers with a profound lack of interest. Each assignment was a reminder of a life he felt no connection to. Each project was an echo, a memory that didn't resonate within him.

He felt a dull ache in his chest, and his eyes found themselves fixated on the window. Outside, the leaves rustled in the breeze, a scene that held no particular interest. He felt as if he was watching a movie of his own life, a movie he had no desire to finish.

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