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 relentless tick-tock of the clock on the departure board felt like a slow, deliberate torture for Sarah. Her flight to London, and her best friend's final theatre performance, was indefinitely postponed. She clenched her jaw, her whole body rigid.

She pushed back a stray strand of hair, her movements jerky and uncoordinated. The pre-flight buzz, the excited anticipation of other passengers, felt like a cruel mockery. She desperately wanted to be there to support her friend.

She stared out the window, watching the rain streak down the glass. The vibrant lights of the city outside seemed to fade into a blur. She felt a deep, abiding sense of isolation.

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