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 world around Daniel felt muted, distant. The yard sale was another landscape he was simply passing through, each step a chore. The items on display held no allure, the conversations of the shoppers seemed to fade into a general background noise. He wandered like a stranger in his own life.

He stopped, his gaze drawn by a familiar sight. There, on a table overflowing with childhood items, was his childhood teddy bear. He recognized the shape, the worn patches, the slight smell of old dust and childhood, it was the bear. A strange current ran through him.

"How much?" he asked, his voice barely audible. The seller, a young boy with a mischievous grin, shrugged. "A quarter." He paid without a word, the bear nestled in his arms.

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