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 flickering neon sign of the diner cast an anemic glow on Arthur's face. He’d been sitting there for hours, nursing a lukewarm coffee, the unopened time capsule a cold weight beside him on the table. The inscription, scratched into the metal, read like an accusation: "For future me, who's probably doing a lot better."

The waitress, a woman with kind eyes and tired lines etched around them, refilled his cup without a word. He looked at her, and then away. He felt a deep ache in his chest, a yearning for something he couldn't quite name. The din of the diner, usually a comforting backdrop, felt like a cacophony today, amplifying his isolation.

He pushed the capsule away, not ready to confront what the past held. The bitter taste of coffee lingered on his tongue, a physical manifestation of his internal state.

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
πŸ˜”0.405
S0.384
无法0.341
L0.337
Suppressed:
de-0.749
la-0.614
l-0.471
/-0.350
!-0.322