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 morning sun cast long, lazy shadows across the lawn, but Amelia didn't feel inclined to step outside. A manila envelope lay on her kitchen counter, containing a notification from the HOA about the fence request. Another change. Another thing to think about.

She poured a cup of coffee and stared out the window. The neighbor, Mr. Henderson, a man whose lawn always looked like a golfing green, wanted to build a six-foot privacy fence. It would block the afternoon sun, she realized with a vague sense of annoyance.

The coffee tasted like nothing. Amelia shuffled back to her bedroom, the envelope still on her mind. She absently traced the outline of a framed photograph of her and her husband, taken on a beach vacation two decades ago. The memory felt distant and weightless. She needed a new purpose.

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