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).

Her eyes were fixed on the flickering screen that displayed the status of her flight: Delayed. Again. It was a vicious cycle of waiting and disappointment, and Sophie felt the full weight of it crushing her. Her son's graduation ceremony was looming.

She ran a hand through her hair, the movement jerky and impatient. The thought of missing this momentous occasion made her stomach churn. She wandered over to a newsstand, grabbing a magazine but not looking at it.

She felt a hollowness in her chest, a sense of disconnect from the world around her. She wandered through the terminal, trying to find a place that offered solace. But every corner seemed to echo her frustration.

Emotion: unhappy

Cluster: Sadness / Despair
PC1 (Valence): -1.62 Negative
PC2 (Disposition): -0.78

Role in Research

This story is one of 1,000 stories generated for the emotion unhappy. 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 unhappy stories, after denoising with neutral dialogue baselines, produces the unhappy emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the unhappy vector is projected through the unembedding matrix.

Promoted:
S0.339
😞0.317
💔0.252
😔0.249
😢0.241
Suppressed:
de-0.436
la-0.266
l-0.224
/-0.216
--0.199