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 air in the tiny apartment felt thick, suffocating. He paced the worn wooden floorboards, each step a reluctant shuffle. The rejection, a curt, impersonal email, lay open on the kitchen table, a constant reminder of his failure. He was unable to eat his breakfast.

He wanted to scream, to lash out, but instead, he simply retreated further into himself. He avoided his phone, afraid of the well-meaning inquiries, the forced positivity. He did not know how he would face the world the next day.

He picked up his guitar, a comforting presence, but the music felt hollow, devoid of the usual joy. Even his passion had been touched by the shadow of the rejection. He gently put it down again.

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