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).

Rain lashed against the bakery window, mirroring the tempest inside Amelia. She slumped on a stool, chin resting on her hand, the warmth of the oven doing little to thaw her. Another customer had raved about "Sunshine Scones" at the new cafe down the street – the very same recipe she'd painstakingly developed over years, the one her grandmother had passed down.

A bitter taste filled her mouth. She hadn't sold a single scone today. Her own attempts at promoting the treats had failed miserably, her brochures gathering dust on the counter. She’d tried a few different names – “Amelia’s Originals”, “Grandma’s Best” – but nothing had stuck.

She picked up a discarded recipe card, her fingers tracing the familiar flour-dusted letters. The ink blurred as a stray tear escaped. The cafe was a beacon of success, bathed in sunshine, while she felt as though she were in the deepest shadows.

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