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).

He felt as though he were wading through thick syrup. The thought of climbing the stairs, of facing the cluttered space above, filled James with a profound fatigue. Still, he forced himself upward, each step a monumental task. The air in the attic was stale, heavy with the ghosts of forgotten things.

He spotted a trunk, its leather cracked and peeling. He knelt before it, his muscles protesting. He lifted the heavy lid. Inside, nestled in tissue paper, was a collection of antique tools. A hammer, a saw, a plane – all meticulously crafted and lovingly cared for.

He stared at them, the details blurring. The precision, the care that went into each piece. A sharp, unfamiliar pang echoed in his chest. Then, it was gone, replaced by the usual void. He let the lid fall shut, the sound echoing in the silent room.

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