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 weight of the duvet pressed down on Michael. He considered staying in bed, as he had for the past several days. The silence of the house was punctuated only by his own shallow breaths. The world outside his window seemed distant, unreachable.

He finally sat up, the effort leaving him breathless. His reflection in the mirror offered a stranger's tired gaze. He hadn't shaved in days. He ran a hand through his tangled hair. There was a dull ache behind his eyes, a persistent thrum of… something he couldn't name.

His mother’s gentle knock startled him. "Honey, breakfast is ready," she called. He felt a wave of guilt wash over him. He was a burden. He pulled himself out of bed and into the hallway. The scent of bacon was supposed to be inviting, but it just made him feel… nothing.

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