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 sunlight felt abrasive on Michael's skin. He felt the weight of the air, thick and oppressive, clinging to him like a second skin. He usually enjoyed the sunshine, but now, it just felt...loud. He had been avoiding work, avoiding friends, avoiding everything. His brother, David, had recently become a father and needed some help. So he'd reluctantly agreed to watch his nephew, Leo, for a couple of hours. Leo, all boundless energy and sticky fingers, was currently "building a spaceship" out of cardboard boxes. The incessant chatter grated on Michael's nerves. He found himself avoiding eye contact, retreating into himself. Later, Leo presented him with a picture: a winged creature with three eyes and a mischievous grin. "Mr. Snugglepuss," Leo announced. Michael felt a strange prickling sensation on the back of his neck.

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