Email Subject Line Classifier

How Email Subject Line Classifier works

Press Load model once: your browser downloads Gemma 4 E2B instruction-tuned (web build) (2.0 GB) from this site and keeps it in its cache. Then add your text and press Classify locally. The model runs on this device using your graphics card, so nothing you enter is sent to a server. Until the model is loaded, or if your device cannot run it, the tool falls back to a simple keyword check and labels the result as the fallback.

Gemma 4 E2B instruction-tuned (web build) is a small open language model from Google. The tool sends it the instruction below plus your text, asks for a JSON answer with fixed fields, and shows each field as a card. It runs at temperature 0, so the same input gives the same answer on the same device, though different graphics cards can word it slightly differently.

Inputs longer than 6,000 characters are cut to that length before they reach the model, and the result says so. The model only sees what you paste: it does not look anything up.

The instruction the model gets

You label email subject lines for a marketer. For each subject line (one per line), pick one type: Urgency (deadline, last chance, ending soon), Curiosity (teases without telling), Benefit (states a result or saving), Update (account notice, report, receipt), Personal (reads like a one-to-one note or question), Offer (discount or free item). Also quote wording that tends to look pushy or spammy (all caps, many exclamation marks, 'free!!!', 'act now'). Do not predict open rates.

What it returns

• Type per subject line: One entry per subject line, written exactly as 'subject → Type: short reason'.
• Overall mix: Which types dominate and which are missing.
• Pushy or spammy wording: Exact words or phrases quoted from the subject lines.
• Lines that are too alike: Pairs of subject lines that say nearly the same thing.

Worked example

The model's output for the built-in sample, recorded on a desktop browser. Your run may word things slightly differently.

Last chance to cut your API costs Your July usage report is ready We saved you 38% on inference yesterday Quick question about your GPU cluster

Type per subject line

Last chance to cut your API costs → Urgency: Deadline implied Your July usage report is ready → Update: Account notice We saved you 38% on inference yesterday → Benefit: States a result Quick question about your GPU cluster → Curiosity: Teases without telling

Overall mix

Urgency, Benefit, Update, Curiosity

Pushy or spammy wording

Last chance act now

Lines that are too alike

We saved you 38% on inference yesterday Last chance to cut your API costs

The model

The files are served from this site, versioned so a cached copy is never stale. Nothing is fetched from a third party while you use the tool.

Limitations

• Small language models make mistakes: they can miss an item, merge two, or state something more confidently than the text supports. Check the result against your input before you rely on it.
• It needs WebGPU and about 8 GB of memory, so it is offered on desktops and laptops, not on phones and tablets. Devices that cannot run it get the keyword fallback, clearly labelled.
• Results describe the input you gave, not the real-world situation behind it. Review them yourself before acting.

Good uses

• Triage SEO and digital marketing notes before deeper review
• Prepare consistent labels for repeat workflows
• Reduce manual sorting on small batches
• Keep sensitive drafts in the browser preview