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 afternoon stretched before him, an endless expanse of gray. James sat on the porch swing, the rhythmic creak of the chains a monotonous counterpoint to the quiet hum of the neighborhood. He hadn’t felt a genuine emotion in what felt like forever. He’d gone to pick up Sarah's laptop, and the title of the document had immediately caught his eye: "The Unfolding."

He’d found the chapters scattered throughout, each one detailing an aspect of his life, his routines, his shortcomings. He felt like a lab rat in a sociological experiment. The protagonist, a man named Mark, seemed to exist solely to serve the plot, a puppet manipulated by the author's whims. He closed the laptop, the screen reflecting his own blank expression.

The swing continued its relentless back-and-forth, carrying him nowhere.

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