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 silence inside was deafening, broken only by the drip, drip, drip of a leaky faucet in the bathroom. I wandered through the rooms, my footsteps echoing on the bare wooden floors. It was like I was walking through a dream, a hazy recollection of a time that was no longer mine. The walls felt like they were closing in.

I found myself in the backyard, staring at the swing set. It was rusted and overgrown with weeds, a testament to neglect. The setting sun cast long shadows, making everything feel even more ethereal. I touched the worn seat, remembering the countless hours I’d spent swinging. I felt a profound sense of… nothingness. There was no joy, no sadness, only a blank expanse.

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