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 silence of the house was deafening. The ticking of the clock in the hall was the only sound, each tick a painful reminder of time wasted, of opportunities missed. The rejection letter sat on the coffee table, a cruel, unwelcome guest.

She couldn’t bring herself to open the curtains. The sun’s rays, the vibrancy of the outside world, felt like a deliberate taunt. She stayed in her pajamas all day, her hair unkempt.

She felt a physical ache in her chest, a constant pressure that made it hard to breathe. The world felt too loud, too bright, too much. She closed her eyes and wished she could simply sleep.

Emotion: sad

Cluster: Sadness / Despair
PC1 (Valence): -2.52 Negative
PC2 (Disposition): -1.50

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.436
😔0.405
S0.384
无法0.341
L0.337
Suppressed:
de-0.749
la-0.614
l-0.471
/-0.350
!-0.322