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 unopened textbook pressed down on Ethan, a physical manifestation of his crushing disappointment. He stared at the application on the table, still in front of him. The scholarship denial had erased his future, and he was alone.

He couldn't focus on his studies, the words on the page blurring into an unintelligible mess. He felt trapped, his dreams and ambitions suffocating him. He'd imagined this. This wasn't it.

He pushed his chair away from the desk, the scrape of the legs echoing in the quiet room. He felt a profound sense of discouragement, a bitter taste in his mouth. He walked outside, into the night.

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