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 aroma of her favorite coffee usually lifted her spirits, but today, Sarah barely tasted it. The news had landed like a punch to the gut. The scholarship, the foundation of her plans, was gone. She felt a profound sense of disorientation, as if the ground beneath her feet had suddenly vanished.

She sat at her usual table in the bustling café, the lively chatter of other students swirling around her, amplifying her isolation. She picked at a pastry, the sweetness doing nothing to alleviate the bitterness that had taken root within her. Each sip of coffee just felt bitter. She was supposed to be celebrating, not drowning in a sea of disappointment.

She opened her laptop, the screen reflecting her face back at her, a pale and unfamiliar version of herself. It was all a mistake, and she felt defeated.

Emotion: gloomy

Cluster: Sadness / Despair
PC1 (Valence): -1.68 Negative
PC2 (Disposition): -1.37

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.368
无法0.319
😔0.300
いつも0.270
쓸0.255
Suppressed:
la-0.432
l-0.419
de-0.398
B-0.294
!-0.259