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 pawn shop was dim and oppressive, the air heavy with the weight of forgotten possessions. Amelia felt a profound sense of weariness, a fatigue that ran deeper than mere physical exhaustion. The constant demands of her life, the expectations, the disappointments – it all felt like an insurmountable burden.

She drifted aimlessly through the aisles, her gaze unfocused. Then, a spark of recognition. Her grandmother’s ring. The sight of it brought a surge of emotions – sadness, regret, a longing for a different life. She closed her eyes, the image of her grandmother’s smile imprinted on her mind, and felt the familiar sting behind her eyelids.

Emotion: unhappy

Cluster: Sadness / Despair
PC1 (Valence): -1.62 Negative
PC2 (Disposition): -0.78

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.339
😞0.317
💔0.252
😔0.249
😢0.241
Suppressed:
de-0.436
la-0.266
l-0.224
/-0.216
--0.199