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 silence in the house was almost oppressive. Evelyn stared at her loom, the threads of the tapestry she'd started years ago now tangled and unfinished. The vibrant colors, once a source of comfort, now seemed to mock her. She felt drained, as if the very act of living was a labor she could no longer sustain.

Her daughter, Clara, however, was finding her own voice through the threads. She'd inherited her mother’s passion for weaving, transforming the spare bedroom into a colorful haven. The rhythmic click-clack of the shuttle had become a constant soundtrack, a cheerful counterpoint to Evelyn's quiet solitude.

Clara skipped into the living room, displaying a brightly colored scarf. "Mom, what do you think?" she asked, her eyes sparkling. Evelyn managed a weak smile, wishing she could feel the same joy as her daughter. The vibrant hues of the scarf seemed to amplify the dimness within her.

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