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 chipped mug warmed Amelia's hands, but the chill in her bones remained. She stared out the rain-streaked window at the monotonous grey sky, mirroring her mood. The biography, “Amelia – A Life Unfolding,” had landed on her doorstep this morning. A glossy cover featuring a smiling version of herself, a self she barely recognized anymore. The words inside, detailing her childhood, her failed attempts at art school, her monotonous office job... They felt like a cage, defining her existence in ways she couldn't escape. Her breath hitched. She felt constricted, a pressure building in her chest, mirroring the tight feeling around the throat.

Emotion: stuck

Cluster: Sadness / Despair
PC1 (Valence): -2.17 Negative
PC2 (Disposition): -0.72

Role in Research

This story is one of 1,000 stories generated for the emotion stuck. 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 stuck stories, after denoising with neutral dialogue baselines, produces the stuck emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the stuck vector is projected through the unembedding matrix.

Promoted:
S0.487
缺乏0.401
L0.361
每天0.348
stagn0.348
Suppressed:
l-0.472
la-0.346
随后-0.322
undamaged-0.268
C-0.263