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 windows of Maya's apartment, mirroring the turmoil in her gut. She chewed on her thumbnail, the taste of metal familiar and unwelcome. Days blurred into a monotonous cycle of lukewarm coffee, scrolling through social media, and the crushing weight of nothingness. She felt a profound emptiness, a yawning chasm where ambition used to reside. She thought of Liam, her best friend, always regaling her with tales of high-powered meetings and complex deals at "Sterling & Finch." She should be happy for him. Instead, a sourness rose in her throat.

Yesterday, she'd seen him. Not at a business lunch as he'd said, but loading boxes at a local storage unit.

Her pulse hammered against her ribs.

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