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).

Rain lashed against the pawn shop's window, mirroring the disquiet brewing within Clara. She hadn't felt the sun on her skin in ages. The routine of her days was a blur of muted colors and indistinct sounds. She drifted through life like a leaf in a stagnant pond. Now she was staring at her grandmother's engagement ring. The gleam of the diamonds offered a flicker of familiarity, a spark of something she thought long gone.

“How much?” she asked, her voice raspy from disuse. The shop owner, a woman with a perpetually tired expression, told her. It was a paltry sum, a testament to the ring's forgotten value. Clara, without a second thought, paid and tucked the ring into her pocket. She wandered outside, into the downpour, feeling a strange sort of hollow satisfaction. The rain felt cold and cleansing.

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