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 harsh fluorescent lights of the pawn shop seemed to drain the color from everything, leaving everything washed-out and grey. Ethan shifted uneasily, the weight of his recent experience pressing heavily on him. He felt as though he were wading through treacle.

Then, his eyes fixed on a ring. It was the one. His grandmother's engagement ring. It was a tangible connection to her, a reminder of the love and stability that had vanished.

He approached the counter, his pace slow, his shoulders slumped. He pointed at the ring, the gesture accompanied by a silent, almost involuntary sigh. The shop was a blur of sound and motion, and he was alone in a sea of despair.

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