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 vibrant decorations of the banquet hall seemed to mock Eleanor. She sat alone at a table near the back, picking at her salad. The clinking of silverware, the murmur of conversations—it all seemed to amplify her discomfort.

She felt a hollowness inside, a void that no amount of food or conversation could fill. The speech, carefully rehearsed, felt like a series of empty phrases. Each time she thought of delivering it, a knot would tighten in her chest.

She watched the people around her, their faces illuminated by the party lights. She felt as though she was observing a play, a performance that she wasn’t a part of. She felt like a dark cloud passing through a sunny day.

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