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 attic air hung thick and heavy, dust motes dancing in the single shaft of sunlight that pierced the gloom. Elias ran a hand through his hair, the gesture slow and deliberate. He'd been doing a lot of that lately – the slow, deliberate actions. His sister, Clara, was already halfway through the trunk, her back to him, humming a tuneless melody.

"Find anything good?" he mumbled, his voice catching in his throat. He felt the weight of the unopened boxes pressing down on him, not just physically, but a deeper, invisible burden.

Clara turned, her face illuminated by a gold locket she held. "Just some old jewelry and moth-eaten shawls. But look at this!" She held out a framed photograph. He squinted. It was their grandmother, but…younger. Vibrant. Alive. A stark contrast to the hollow ache that had settled in his own chest.

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